{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":741989385,"defaultBranch":"main","name":"llm-graph-builder","ownerLogin":"neo4j-labs","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2024-01-11T14:31:18.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/42673396?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1725963304.0","currentOid":""},"activityList":{"items":[{"before":"169c2727820ea0469c88bf6ccfa10a46617442fe","after":"a12b7cd8f9089f13810a50f4859631edf5ae7b2e","ref":"refs/heads/communities","pushedAt":"2024-09-10T16:54:02.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vasanthasaikalluri","name":null,"path":"/vasanthasaikalluri","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/165021735?s=80&v=4"},"commit":{"message":"added local search","shortMessageHtmlLink":"added local search"}},{"before":null,"after":"13c7bc839ba945454812bf29d88886d68428330d","ref":"refs/heads/prompt_enhancement","pushedAt":"2024-09-10T10:15:04.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"aashipandya","name":null,"path":"/aashipandya","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156318202?s=80&v=4"},"commit":{"message":"added chnages to graph schema","shortMessageHtmlLink":"added chnages to graph schema"}},{"before":"0cd5848ffae7e0abd2fbf8c4835ba96cfea7a2cf","after":"d33c25e1535243609fb754a65cb9927a03d5c417","ref":"refs/heads/727-add-communities-to-graph-viz","pushedAt":"2024-09-10T08:32:05.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"vasanthasaikalluri","name":null,"path":"/vasanthasaikalluri","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/165021735?s=80&v=4"},"commit":{"message":"Merge branch '727-add-communities-to-graph-viz' of https://github.com/neo4j-labs/llm-graph-builder into 727-add-communities-to-graph-viz","shortMessageHtmlLink":"Merge branch '727-add-communities-to-graph-viz' of <a href=\"https://github.com/neo4j-labs/llm-graph-builder\">https://github.com…</a>"}},{"before":"e9e68ea647f847887a05c8bd09fca35ea125d431","after":"0cd5848ffae7e0abd2fbf8c4835ba96cfea7a2cf","ref":"refs/heads/727-add-communities-to-graph-viz","pushedAt":"2024-09-10T07:20:43.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"filter logic missing checks","shortMessageHtmlLink":"filter logic missing checks"}},{"before":"806ac58d4b122b53801fde37b76cf5b3792af8a1","after":"e9e68ea647f847887a05c8bd09fca35ea125d431","ref":"refs/heads/727-add-communities-to-graph-viz","pushedAt":"2024-09-10T07:06:43.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"filter logic","shortMessageHtmlLink":"filter logic"}},{"before":"fe9e38e2ab00ed5eb012287b30092d0fbcfda8f1","after":"806ac58d4b122b53801fde37b76cf5b3792af8a1","ref":"refs/heads/727-add-communities-to-graph-viz","pushedAt":"2024-09-09T14:56:57.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"Merge branch 'graph_communities' of https://github.com/neo4j-labs/llm-graph-builder into 727-add-communities-to-graph-viz","shortMessageHtmlLink":"Merge branch 'graph_communities' of <a href=\"https://github.com/neo4j-labs/llm-graph-builder\">https://github.com/neo4j-labs/llm…</a>"}},{"before":"c666c368b1ce6c09d06d90f82451fdce7ad56629","after":"fe9e38e2ab00ed5eb012287b30092d0fbcfda8f1","ref":"refs/heads/727-add-communities-to-graph-viz","pushedAt":"2024-09-09T14:54:10.000Z","pushType":"push","commitsCount":17,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"checkbox addition","shortMessageHtmlLink":"checkbox addition"}},{"before":"7ff05cc10e59e1d6cadf3505534928fd15b68502","after":"13c7bc839ba945454812bf29d88886d68428330d","ref":"refs/heads/DEV","pushedAt":"2024-09-09T14:30:34.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"abhishekkumar-27","name":null,"path":"/abhishekkumar-27","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/164544129?s=80&v=4"},"commit":{"message":"added chnages to graph schema","shortMessageHtmlLink":"added chnages to graph schema"}},{"before":"a0ede78c622837ccdef058412a46b7f5dec22e52","after":"7b14ed639d98eb75c9a30353fe6450419bf5ee71","ref":"refs/heads/725-add-checkbox-for-create_communities","pushedAt":"2024-09-09T11:57:50.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"graph query","shortMessageHtmlLink":"graph query"}},{"before":"1aa28429a283faef97126b345ab030bc35969110","after":"06b2c58875429f77e3afab4e446cacadcbbdab13","ref":"refs/heads/main","pushedAt":"2024-09-09T09:38:38.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"aashipandya","name":null,"path":"/aashipandya","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156318202?s=80&v=4"},"commit":{"message":"Staging to main (#735)\n\n* Dev (#537)\r\n\r\n* format fixes and graph schema indication fix\r\n\r\n* Update README.md\r\n\r\n* added chat modes variable in env updated the readme\r\n\r\n* spell fix\r\n\r\n* added the chat mode in env table\r\n\r\n* added the logos\r\n\r\n* fixed the overflow issues\r\n\r\n* removed the extra fix\r\n\r\n* Fixed specific scenario  \"when the text from schema closes it should reopen the previous modal\"\r\n\r\n* readme changes\r\n\r\n* removed dev console logs\r\n\r\n* added new retrieval query (#533)\r\n\r\n* format fixes and tab rendering fix\r\n\r\n* fixed the setting modal reopen issue\r\n\r\n---------\r\n\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\n\r\n* disabled the sumbit buttom on loading\r\n\r\n* Deduplication tab (#566)\r\n\r\n* de-duplication API\r\n\r\n* Update De-Duplicate query\r\n\r\n* created the Deduplication tab\r\n\r\n* added the API service\r\n\r\n* added the removeable tags for similar nodes in deduplication tab\r\n\r\n* Integrate Tag\r\n\r\n* added GraphLabel\r\n\r\n* added loader state\r\n\r\n* added the merge service\r\n\r\n* integrated the merge API\r\n\r\n* Merge Query issue fixed\r\n\r\n* Auto refresh the duplicate nodes after merging operation\r\n\r\n* added the description for de duplication\r\n\r\n* reset on merging\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Update frontend_docs.adoc (#538)\r\n\r\n* Update frontend_docs.adoc\r\n\r\n* doc update\r\n\r\n* Images\r\n\r\n* Images folder change\r\n\r\n* Images folder change\r\n\r\n* test image\r\n\r\n* Update frontend_docs.adoc\r\n\r\n* image change\r\n\r\n* Update frontend_docs.adoc\r\n\r\n* Update frontend_docs.adoc\r\n\r\n* added the Graph Mode SS\r\n\r\n* added the Query SS\r\n\r\n* Update frontend_docs.adoc\r\n\r\n* conflics fix\r\n\r\n* conflict fix\r\n\r\n* Update frontend_docs.adoc\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* updated langchain versions (#565)\r\n\r\n* Update the De-Duplication query\r\n\r\n* Node relationship id type none issue (#547)\r\n\r\n* de-duplication API\r\n\r\n* Update De-Duplicate query\r\n\r\n* Issue fixed Nodes,Relationship Id and Type None or Blank\r\n\r\n* added the tooltips\r\n\r\n* type fix\r\n\r\n* Unneccory import\r\n\r\n* added score threshold and added some error handling (#571)\r\n\r\n* Update requirements.txt\r\n\r\n* Tooltip and other UI fixes (#572)\r\n\r\n* Staging To Main (#495)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n* Dev (#433)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n---------\r\n\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: Ajay Meena <meenajy1996@gmail.com>\r\nCo-authored-by: Morgan Senechal <morgan@neo4j.com>\r\nCo-authored-by: karanchellani <142801957+karanchellani@users.noreply.github.com>\r\n\r\n* fixed gcs status message issue\r\n\r\n* added if check for failed count\r\n\r\n* Null issue Fixed from backend for upload API and graph_document when model name mismatch\r\n\r\n* added word break issue\r\n\r\n* Added neo4j-rust-ext\r\n\r\n* processing time estimation based on bytes\r\n\r\n* File extension upper case fixed, File delete from GCS or local based on env variable.\r\n\r\n* timer per byte\r\n\r\n* Update Dockerfile\r\n\r\n* Adding sort rows on the table (#451)\r\n\r\n* Gcs upload folder hashed (#453)\r\n\r\n* implement foldername hashed in GCS bucket uplaod\r\n\r\n* Raise exception if invalid model selected\r\n\r\n* folder name for gcs upload\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* upload all unstructuredfiles to gcs (#455)\r\n\r\n* Mofified chunk query (#454)\r\n\r\n* Added libre office for fixing error -- soffice command was not found. Please install libreoffice\r\non your system and try again.\r\n\r\n- Install instructions: https://www.libreoffice.org/get-help/install-howto/\r\n- Mac: https://formulae.brew.sh/cask/libreoffice\r\n- Debian: https://wiki.debian.org/LibreOffice\"\r\n\r\n* Fix the PARTIAL CONTENT issue\r\n\r\n* File-table no data found (#456)\r\n\r\n* 'file-table''\r\n\r\n* review comment\r\n\r\n* Llm format change (#459)\r\n\r\n* changed the llm models format to lowercase\r\n\r\n* added the error message\r\n\r\n* llm model changes\r\n\r\n* format fixes\r\n\r\n* removed unused import\r\n\r\n* added the capitalize method\r\n\r\n* delete files from merged_file_path only if source is local file\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* commented total page code (#460)\r\n\r\n* format fixes\r\n\r\n* removed the disabled check on dropdown\r\n\r\n* Large file env\r\n\r\n* DEV to STAGING (#461)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n* fixed gcs status message issue\r\n\r\n* added if check for failed count\r\n\r\n* Null issue Fixed from backend for upload API and graph_document when model name mismatch\r\n\r\n* added word break issue\r\n\r\n* Added neo4j-rust-ext\r\n\r\n* processing time estimation based on bytes\r\n\r\n* File extension upper case fixed, File delete from GCS or local based on env variable.\r\n\r\n* timer per byte\r\n\r\n* Update Dockerfile\r\n\r\n* Adding sort rows on the table (#451)\r\n\r\n* Gcs upload folder hashed (#453)\r\n\r\n* implement foldername hashed in GCS bucket uplaod\r\n\r\n* Raise exception if invalid model selected\r\n\r\n* folder name for gcs upload\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* upload all unstructuredfiles to gcs (#455)\r\n\r\n* Mofified chunk query (#454)\r\n\r\n* Added libre office for fixing error -- soffice command was not found. Please install libreoffice\r\non your system and try again.\r\n\r\n- Install instructions: https://www.libreoffice.org/get-help/install-howto/\r\n- Mac: https://formulae.brew.sh/cask/libreoffice\r\n- Debian: https://wiki.debian.org/LibreOffice\"\r\n\r\n* Fix the PARTIAL CONTENT issue\r\n\r\n* File-table no data found (#456)\r\n\r\n* 'file-table''\r\n\r\n* review comment\r\n\r\n* Llm format change (#459)\r\n\r\n* changed the llm models format to lowercase\r\n\r\n* added the error message\r\n\r\n* llm model changes\r\n\r\n* format fixes\r\n\r\n* removed unused import\r\n\r\n* added the capitalize method\r\n\r\n* delete files from merged_file_path only if source is local file\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* commented total page code (#460)\r\n\r\n* format fixes\r\n\r\n* removed the disabled check on dropdown\r\n\r\n* Large file env\r\n\r\n---------\r\n\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: Ajay Meena <meenajy1996@gmail.com>\r\nCo-authored-by: Morgan Senechal <morgan@neo4j.com>\r\nCo-authored-by: karanchellani <142801957+karanchellani@users.noreply.github.com>\r\n\r\n* DEV to STAGING (#462)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n* fixed gcs status message issue\r\n\r\n* added if check for failed count\r\n\r\n* Null issue Fixed from backend for upload API and graph_document when model name mismatch\r\n\r\n* added word break issue\r\n\r\n* Added neo4j-rust-ext\r\n\r\n* processing time estimation based on bytes\r\n\r\n* File extension upper case fixed, File delete from GCS or local based on env variable.\r\n\r\n* timer per byte\r\n\r\n* Update Dockerfile\r\n\r\n* Adding sort rows on the table (#451)\r\n\r\n* Gcs upload folder hashed (#453)\r\n\r\n* implement foldername hashed in GCS bucket uplaod\r\n\r\n* Raise exception if invalid model selected\r\n\r\n* folder name for gcs upload\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* upload all unstructuredfiles to gcs (#455)\r\n\r\n* Mofified chunk query (#454)\r\n\r\n* Added libre office for fixing error -- soffice command was not found. Please install libreoffice\r\non your system and try again.\r\n\r\n- Install instructions: https://www.libreoffice.org/get-help/install-howto/\r\n- Mac: https://formulae.brew.sh/cask/libreoffice\r\n- Debian: https://wiki.debian.org/LibreOffice\"\r\n\r\n* Fix the PARTIAL CONTENT issue\r\n\r\n* File-table no data found (#456)\r\n\r\n* 'file-table''\r\n\r\n* review comment\r\n\r\n* Llm format change (#459)\r\n\r\n* changed the llm models format to lowercase\r\n\r\n* added the error message\r\n\r\n* llm model changes\r\n\r\n* format fixes\r\n\r\n* removed unused import\r\n\r\n* added the capitalize method\r\n\r\n* delete files from merged_file_path only if source is local file\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* commented total page code (#460)\r\n\r\n* format fixes\r\n\r\n* removed the disabled check on dropdown\r\n\r\n* Large file env\r\n\r\n---------\r\n\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: Ajay Meena <meenajy1996@gmail.com>\r\nCo-authored-by: Morgan Senechal <morgan@neo4j.com>\r\nCo-authored-by: karanchellani <142801957+karanchellani@users.noreply.github.com>\r\n\r\n* added upload api\r\n\r\n* changed the dropzone error message\r\n\r\n* Dev to staging (#466)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n* fixed gcs status message issue\r\n\r\n* added if check for failed count\r\n\r\n* Null issue Fixed from backend for upload API and graph_document when model name mismatch\r\n\r\n* added word break issue\r\n\r\n* Added neo4j-rust-ext\r\n\r\n* processing time estimation based on bytes\r\n\r\n* File extension upper case fixed, File delete from GCS or local based on env variable.\r\n\r\n* timer per byte\r\n\r\n* Update Dockerfile\r\n\r\n* Adding sort rows on the table (#451)\r\n\r\n* Gcs upload folder hashed (#453)\r\n\r\n* implement foldername hashed in GCS bucket uplaod\r\n\r\n* Raise exception if invalid model selected\r\n\r\n* folder name for gcs upload\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* upload all unstructuredfiles to gcs (#455)\r\n\r\n* Mofified chunk query (#454)\r\n\r\n* Added libre office for fixing error -- soffice command was not found. Please install libreoffice\r\non your system and try again.\r\n\r\n- Install instructions: https://www.libreoffice.org/get-help/install-howto/\r\n- Mac: https://formulae.brew.sh/cask/libreoffice\r\n- Debian: https://wiki.debian.org/LibreOffice\"\r\n\r\n* Fix the PARTIAL CONTENT issue\r\n\r\n* File-table no data found (#456)\r\n\r\n* 'file-table''\r\n\r\n* review comment\r\n\r\n* Llm format change (#459)\r\n\r\n* changed the llm models format to lowercase\r\n\r\n* added the error message\r\n\r\n* llm model changes\r\n\r\n* format fixes\r\n\r\n* removed unused import\r\n\r\n* added the capitalize method\r\n\r\n* delete files from merged_file_path only if source is local file\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* commented total page code (#460)\r\n\r\n* format fixes\r\n\r\n* removed the disabled check on dropdown\r\n\r\n* Large file env\r\n\r\n* added upload api\r\n\r\n* changed the dropzone error message\r\n\r\n---------\r\n\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: Ajay Meena <meenajy1996@gmail.com>\r\nCo-auth…","shortMessageHtmlLink":"Staging to main (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2513000516\" data-permission-text=\"Title is private\" data-url=\"https://github.com/neo4j-labs/llm-graph-builder/issues/735\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/neo4j-labs/llm-graph-builder/pull/735/hovercard\" href=\"https://github.com/neo4j-labs/llm-graph-builder/pull/735\">#735</a>)"}},{"before":"b7355ba4e8faf6b68cb9735dadc4f6c4b61c1b4a","after":"758a506850930d321b8788c93518b5ec46f97fea","ref":"refs/heads/STAGING","pushedAt":"2024-09-09T09:30:54.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"Merge branch 'main' into STAGING","shortMessageHtmlLink":"Merge branch 'main' into STAGING"}},{"before":"122f6a647247c257e859296cb11e3af7338334a4","after":"7ff05cc10e59e1d6cadf3505534928fd15b68502","ref":"refs/heads/DEV","pushedAt":"2024-09-09T08:54:07.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"praveshkumar1988","name":"Pravesh Kumar","path":"/praveshkumar1988","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/121786590?s=80&v=4"},"commit":{"message":"youtube transcript issue  (#736)\n\n* Implement GoogleApiYoutubeLoader for youtube transcript\r\n\r\n* Url encoding issue fixed for youtube URL\r\n\r\n* Get transcript using YouTubeTranscriptApi","shortMessageHtmlLink":"youtube transcript issue (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2513342223\" data-permission-text=\"Title is private\" data-url=\"https://github.com/neo4j-labs/llm-graph-builder/issues/736\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/neo4j-labs/llm-graph-builder/pull/736/hovercard\" href=\"https://github.com/neo4j-labs/llm-graph-builder/pull/736\">#736</a>)"}},{"before":"351903f3329465320e6274436d6d988f4e91123b","after":"edeeec1f36bd34ea3f2a6d8a9806bbd1cf69f8ed","ref":"refs/heads/googleApiYoutubeLoader_implement","pushedAt":"2024-09-09T08:51:38.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"praveshkumar1988","name":"Pravesh Kumar","path":"/praveshkumar1988","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/121786590?s=80&v=4"},"commit":{"message":"Get transcript using YouTubeTranscriptApi","shortMessageHtmlLink":"Get transcript using YouTubeTranscriptApi"}},{"before":"b6d079af45992dac72e2f25655dc56126a9637ba","after":"351903f3329465320e6274436d6d988f4e91123b","ref":"refs/heads/googleApiYoutubeLoader_implement","pushedAt":"2024-09-09T07:32:48.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"praveshkumar1988","name":"Pravesh Kumar","path":"/praveshkumar1988","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/121786590?s=80&v=4"},"commit":{"message":"Url encoding issue fixed for youtube URL","shortMessageHtmlLink":"Url encoding issue fixed for youtube URL"}},{"before":"41b43555eb3377de4209110058811135d6601c4f","after":"e9a33b880d6bc267bc573da736604dd275ff448a","ref":"refs/heads/retry_processing","pushedAt":"2024-09-09T05:47:02.000Z","pushType":"push","commitsCount":36,"pusher":{"login":"aashipandya","name":null,"path":"/aashipandya","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156318202?s=80&v=4"},"commit":{"message":"updated node count for start from begnning","shortMessageHtmlLink":"updated node count for start from begnning"}},{"before":"1222942539022e0c3ea0ee79dca9845fc6c95d67","after":"0c278de458c4d09bce1dc4ac277354a0c21137d3","ref":"refs/heads/graph_communities","pushedAt":"2024-09-06T16:28:44.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"Add communities check and show respective chat modes (#729)\n\n* DataScience icon addition\r\n\r\n* added checkbox to create_communities\r\n\r\n* added conditionall check for community chat modes\r\n\r\n---------\r\n\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>","shortMessageHtmlLink":"Add communities check and show respective chat modes (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2507420088\" data-permission-text=\"Title is private\" data-url=\"https://github.com/neo4j-labs/llm-graph-builder/issues/729\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/neo4j-labs/llm-graph-builder/pull/729/hovercard\" href=\"https://github.com/neo4j-labs/llm-graph-builder/pull/729\">#729</a>)"}},{"before":"0db94cc2fdd4cd4c8136888d4852271fe857e9f8","after":"a0ede78c622837ccdef058412a46b7f5dec22e52","ref":"refs/heads/725-add-checkbox-for-create_communities","pushedAt":"2024-09-06T16:28:29.000Z","pushType":"push","commitsCount":4,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"checkbox check uncheck change","shortMessageHtmlLink":"checkbox check uncheck change"}},{"before":"ebff81be8fe184dc4684bc73dfdb9fc2cfd33ad4","after":"be731c8681874bf59fa017b62195473305d4dcdb","ref":"refs/heads/add-communities-check-and-show-respective-chat-modes","pushedAt":"2024-09-06T16:03:37.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"Merge branch 'graph_communities' into add-communities-check-and-show-respective-chat-modes","shortMessageHtmlLink":"Merge branch 'graph_communities' into add-communities-check-and-show-…"}},{"before":"64d5a001d45b928bb6ca69657722d89408b75f74","after":"0db94cc2fdd4cd4c8136888d4852271fe857e9f8","ref":"refs/heads/725-add-checkbox-for-create_communities","pushedAt":"2024-09-06T16:01:09.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"format fixes","shortMessageHtmlLink":"format fixes"}},{"before":"66b6f3260583d83f435945ad0114944b452e49c5","after":"64d5a001d45b928bb6ca69657722d89408b75f74","ref":"refs/heads/725-add-checkbox-for-create_communities","pushedAt":"2024-09-06T15:59:33.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"isGdsVal change","shortMessageHtmlLink":"isGdsVal change"}},{"before":"953b042cec4159fd0302ee03bab289d400acc066","after":"66b6f3260583d83f435945ad0114944b452e49c5","ref":"refs/heads/725-add-checkbox-for-create_communities","pushedAt":"2024-09-06T15:56:03.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"Merge branch 'graph_communities' into 725-add-checkbox-for-create_communities","shortMessageHtmlLink":"Merge branch 'graph_communities' into 725-add-checkbox-for-create_com…"}},{"before":"f34fd3703b0643ec6b37ddbd6f7a5d9ba99bc02c","after":"953b042cec4159fd0302ee03bab289d400acc066","ref":"refs/heads/725-add-checkbox-for-create_communities","pushedAt":"2024-09-06T15:55:13.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"icon changes","shortMessageHtmlLink":"icon changes"}},{"before":"10ef37143ad57a621c27d5070e666bd4f80525d7","after":null,"ref":"refs/heads/dataScience_check","pushedAt":"2024-09-06T14:57:37.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"}},{"before":"c666c368b1ce6c09d06d90f82451fdce7ad56629","after":"1222942539022e0c3ea0ee79dca9845fc6c95d67","ref":"refs/heads/graph_communities","pushedAt":"2024-09-06T14:57:25.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"Science Molecule & database icon addition (#722)\n\n* DataScience icon addition\r\n\r\n* added gds status to connect call\r\n\r\n* icon stroke changes\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>","shortMessageHtmlLink":"Science Molecule &amp; database icon addition (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2505508892\" data-permission-text=\"Title is private\" data-url=\"https://github.com/neo4j-labs/llm-graph-builder/issues/722\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/neo4j-labs/llm-graph-builder/pull/722/hovercard\" href=\"https://github.com/neo4j-labs/llm-graph-builder/pull/722\">#722</a>)"}},{"before":"6f9b8ebc0bf90f2e69115ba600a35d5772039c23","after":"f34fd3703b0643ec6b37ddbd6f7a5d9ba99bc02c","ref":"refs/heads/725-add-checkbox-for-create_communities","pushedAt":"2024-09-06T10:53:06.000Z","pushType":"push","commitsCount":4,"pusher":{"login":"prakriti-solankey","name":"Prakriti Solankey","path":"/prakriti-solankey","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156313631?s=80&v=4"},"commit":{"message":"isgds active check","shortMessageHtmlLink":"isgds active check"}},{"before":"e574299c3edf1eee6f8a6cfc3601e5f9fb5ed86e","after":"b7355ba4e8faf6b68cb9735dadc4f6c4b61c1b4a","ref":"refs/heads/STAGING","pushedAt":"2024-09-06T09:08:42.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"aashipandya","name":null,"path":"/aashipandya","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156318202?s=80&v=4"},"commit":{"message":"DEV to STAGING (#732)\n\n* connection _check\r\n\r\n* Fix typo: correct 'josn_obj' to 'json_obj' (#697)\r\n\r\n* Staging To Main (#495)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n* Dev (#433)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n---------\r\n\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: Ajay Meena <meenajy1996@gmail.com>\r\nCo-authored-by: Morgan Senechal <morgan@neo4j.com>\r\nCo-authored-by: karanchellani <142801957+karanchellani@users.noreply.github.com>\r\n\r\n* fixed gcs status message issue\r\n\r\n* added if check for failed count\r\n\r\n* Null issue Fixed from backend for upload API and graph_document when model name mismatch\r\n\r\n* added word break issue\r\n\r\n* Added neo4j-rust-ext\r\n\r\n* processing time estimation based on bytes\r\n\r\n* File extension upper case fixed, File delete from GCS or local based on env variable.\r\n\r\n* timer per byte\r\n\r\n* Update Dockerfile\r\n\r\n* Adding sort rows on the table (#451)\r\n\r\n* Gcs upload folder hashed (#453)\r\n\r\n* implement foldername hashed in GCS bucket uplaod\r\n\r\n* Raise exception if invalid model selected\r\n\r\n* folder name for gcs upload\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* upload all unstructuredfiles to gcs (#455)\r\n\r\n* Mofified chunk query (#454)\r\n\r\n* Added libre office for fixing error -- soffice command was not found. Please install libreoffice\r\non your system and try again.\r\n\r\n- Install instructions: https://www.libreoffice.org/get-help/install-howto/\r\n- Mac: https://formulae.brew.sh/cask/libreoffice\r\n- Debian: https://wiki.debian.org/LibreOffice\"\r\n\r\n* Fix the PARTIAL CONTENT issue\r\n\r\n* File-table no data found (#456)\r\n\r\n* 'file-table''\r\n\r\n* review comment\r\n\r\n* Llm format change (#459)\r\n\r\n* changed the llm models format to lowercase\r\n\r\n* added the error message\r\n\r\n* llm model changes\r\n\r\n* format fixes\r\n\r\n* removed unused import\r\n\r\n* added the capitalize method\r\n\r\n* delete files from merged_file_path only if source is local file\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* commented total page code (#460)\r\n\r\n* format fixes\r\n\r\n* removed the disabled check on dropdown\r\n\r\n* Large file env\r\n\r\n* DEV to STAGING (#461)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n* fixed gcs status message issue\r\n\r\n* added if check for failed count\r\n\r\n* Null issue Fixed from backend for upload API and graph_document when model name mismatch\r\n\r\n* added word break issue\r\n\r\n* Added neo4j-rust-ext\r\n\r\n* processing time estimation based on bytes\r\n\r\n* File extension upper case fixed, File delete from GCS or local based on env variable.\r\n\r\n* timer per byte\r\n\r\n* Update Dockerfile\r\n\r\n* Adding sort rows on the table (#451)\r\n\r\n* Gcs upload folder hashed (#453)\r\n\r\n* implement foldername hashed in GCS bucket uplaod\r\n\r\n* Raise exception if invalid model selected\r\n\r\n* folder name for gcs upload\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* upload all unstructuredfiles to gcs (#455)\r\n\r\n* Mofified chunk query (#454)\r\n\r\n* Added libre office for fixing error -- soffice command was not found. Please install libreoffice\r\non your system and try again.\r\n\r\n- Install instructions: https://www.libreoffice.org/get-help/install-howto/\r\n- Mac: https://formulae.brew.sh/cask/libreoffice\r\n- Debian: https://wiki.debian.org/LibreOffice\"\r\n\r\n* Fix the PARTIAL CONTENT issue\r\n\r\n* File-table no data found (#456)\r\n\r\n* 'file-table''\r\n\r\n* review comment\r\n\r\n* Llm format change (#459)\r\n\r\n* changed the llm models format to lowercase\r\n\r\n* added the error message\r\n\r\n* llm model changes\r\n\r\n* format fixes\r\n\r\n* removed unused import\r\n\r\n* added the capitalize method\r\n\r\n* delete files from merged_file_path only if source is local file\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* commented total page code (#460)\r\n\r\n* format fixes\r\n\r\n* removed the disabled check on dropdown\r\n\r\n* Large file env\r\n\r\n---------\r\n\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: Ajay Meena <meenajy1996@gmail.com>\r\nCo-authored-by: Morgan Senechal <morgan@neo4j.com>\r\nCo-authored-by: karanchellani <142801957+karanchellani@users.noreply.github.com>\r\n\r\n* DEV to STAGING (#462)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n* fixed gcs status message issue\r\n\r\n* added if check for failed count\r\n\r\n* Null issue Fixed from backend for upload API and graph_document when model name mismatch\r\n\r\n* added word break issue\r\n\r\n* Added neo4j-rust-ext\r\n\r\n* processing time estimation based on bytes\r\n\r\n* File extension upper case fixed, File delete from GCS or local based on env variable.\r\n\r\n* timer per byte\r\n\r\n* Update Dockerfile\r\n\r\n* Adding sort rows on the table (#451)\r\n\r\n* Gcs upload folder hashed (#453)\r\n\r\n* implement foldername hashed in GCS bucket uplaod\r\n\r\n* Raise exception if invalid model selected\r\n\r\n* folder name for gcs upload\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* upload all unstructuredfiles to gcs (#455)\r\n\r\n* Mofified chunk query (#454)\r\n\r\n* Added libre office for fixing error -- soffice command was not found. Please install libreoffice\r\non your system and try again.\r\n\r\n- Install instructions: https://www.libreoffice.org/get-help/install-howto/\r\n- Mac: https://formulae.brew.sh/cask/libreoffice\r\n- Debian: https://wiki.debian.org/LibreOffice\"\r\n\r\n* Fix the PARTIAL CONTENT issue\r\n\r\n* File-table no data found (#456)\r\n\r\n* 'file-table''\r\n\r\n* review comment\r\n\r\n* Llm format change (#459)\r\n\r\n* changed the llm models format to lowercase\r\n\r\n* added the error message\r\n\r\n* llm model changes\r\n\r\n* format fixes\r\n\r\n* removed unused import\r\n\r\n* added the capitalize method\r\n\r\n* delete files from merged_file_path only if source is local file\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* commented total page code (#460)\r\n\r\n* format fixes\r\n\r\n* removed the disabled check on dropdown\r\n\r\n* Large file env\r\n\r\n---------\r\n\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: Ajay Meena <meenajy1996@gmail.com>\r\nCo-authored-by: Morgan Senechal <morgan@neo4j.com>\r\nCo-authored-by: karanchellani <142801957+karanchellani@users.noreply.github.com>\r\n\r\n* added upload api\r\n\r\n* changed the dropzone error message\r\n\r\n* Dev to staging (#466)\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* recent merges\r\n\r\n* pdf deletion due to out of diskspace\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* added the default page size\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* offset in chunks (#389)\r\n\r\n* page number in gcs loader (#393)\r\n\r\n* added youtube timestamps (#392)\r\n\r\n* chat pop up button (#387)\r\n\r\n* expand\r\n\r\n* minimize-icon\r\n\r\n* css changes\r\n\r\n* chat history\r\n\r\n* chatbot wider Side Nav\r\n\r\n* expand icon\r\n\r\n* chatbot UI\r\n\r\n* Delete\r\n\r\n* merge fixes\r\n\r\n* code suggestions\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* chunks create before extraction using is_pre_process variable (#383)\r\n\r\n* chunks create before extraction using is_pre_process variable\r\n\r\n* Return total pages for Model\r\n\r\n* update requirement.txt\r\n\r\n* total pages on uplaod API\r\n\r\n* added the Confirmation Dialog\r\n\r\n* added the selected files into the confirmation modal\r\n\r\n* format and lint fixes\r\n\r\n* added the stop watch image\r\n\r\n* fileselection on alert dialog\r\n\r\n* Add timeout in docker for gunicorn workers\r\n\r\n* Add cancel icon to info popup (#384)\r\n\r\n* Info Modal Changes\r\n\r\n* css changes\r\n\r\n* recent merges\r\n\r\n* Integration_qa test (#375)\r\n\r\n* Test IntegrationQA added\r\n\r\n* update test cases\r\n\r\n* update test\r\n\r\n* update node count assertions\r\n\r\n* test changes\r\n\r\n* update changes\r\n\r\n* modification test\r\n\r\n* Code refatctor test cases\r\n\r\n* Handle allowedlist issue in test\r\n\r\n* test changes\r\n\r\n* update test\r\n\r\n* test case execution\r\n\r\n* test chatbot updates\r\n\r\n* test case update file\r\n\r\n* added file\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* fixed status blank issue\r\n\r\n* Rendering the file name instead of link for gcs and s3 sources in the info modal\r\n\r\n* added the default page size\r\n\r\n* Convert is_cancelled value from string to bool\r\n\r\n* Issue fixed Processed chunked as 0 when file re-process again\r\n\r\n* Youtube timestamps (#386)\r\n\r\n* Wikipedia source to accept all valid urls\r\n\r\n* wikipedia url to support multiple languages\r\n\r\n* integrated wiki langauge param for extract api\r\n\r\n* Youtube video timestamps\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* groq llm integration backend (#286)\r\n\r\n* groq llm integration backend\r\n\r\n* groq and description in node properties\r\n\r\n* added groq in options\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Save Total Pages in DB\r\n\r\n* Added total Pages\r\n\r\n* file selection when we didn't select anything from Main table\r\n\r\n* added the danger icon only for large files\r\n\r\n* added the overflow for more files and file selection for all new files\r\n\r\n* moved the interface to types\r\n\r\n* added the icon accoroding to the source\r\n\r\n* set total page for wiki and youtube\r\n\r\n* h3 heading\r\n\r\n* merge\r\n\r\n* updated the alert on basis if total pages\r\n\r\n* deleted chunks\r\n\r\n* polling based on total pages\r\n\r\n* isNan check\r\n\r\n* large file based on file size for s3 and gcs\r\n\r\n* file source in server side event\r\n\r\n* time calculation based on chunks for gcs and s3\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* fixed the layout issue\r\n\r\n* Populate graph schema (#399)\r\n\r\n* crreate new endpoint populate_graph_schema and update the query for getting lables from DB\r\n\r\n* Added main.py changes\r\n\r\n* conditionally-including-the-gcs-login-flow-in-gcs-as-source (#396)\r\n\r\n* added the condtion\r\n\r\n* removed llms\r\n\r\n* Fixed issue : Remove extra unused param\r\n\r\n* get emb only if used (#278)\r\n\r\n* Chatbot chunks (#402)\r\n\r\n* Added file name to the content  sent to LLM\r\n\r\n* added chunk text in the response\r\n\r\n* increased the docs parts sent to llm\r\n\r\n* Modified graph query\r\n\r\n* mardown rendering\r\n\r\n* youtube starttime\r\n\r\n* icons\r\n\r\n* offset changes\r\n\r\n* removed the files due to codespace space issue\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user (#405)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* fixed css issue\r\n\r\n* fixed status blank issue\r\n\r\n* Modified response when no docs is retrived (#413)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc (#410)\r\n\r\n* Fixed env/docker-compose for local deployments + README doc\r\n\r\n* wrong place for ENV in README\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* by default, removed langsmith + fixed knn score string to float\r\n\r\n* Fixed strings in docker-compose env\r\n\r\n* Added requirements (neo4j 5.15 or later, APOC, and instructions for Neo4j Desktop)\r\n\r\n* Missed the TIME_PER_PAGE env, was causing NaN issue in the approx time processing notification. fixed that\r\n\r\n* Support for all unstructured files (#401)\r\n\r\n* all unstructured files\r\n\r\n* responsiveness\r\n\r\n* added file type\r\n\r\n* added the extensions\r\n\r\n* spell mistake\r\n\r\n* ppt file changes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Settings modal to support generating the labels from the llm by using text given by user with checkbox (#415)\r\n\r\n* added the json\r\n\r\n* added schema from text dialog\r\n\r\n* integrated the schemaAPI\r\n\r\n* added the alert\r\n\r\n* resize fixes\r\n\r\n* Extract schema using direct ChatOpenAI API and Chain\r\n\r\n* integrated the checkbox for schema to text dialog\r\n\r\n* Update SettingModal.tsx\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* gcs file content read via storage client (#417)\r\n\r\n* gcs file content read via storage client\r\n\r\n* added the access token the file state\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* pypdf2 to read files from gcs (#420)\r\n\r\n* 407 remove driver from frontend (#416)\r\n\r\n* removed driver\r\n\r\n* removed API\r\n\r\n* connecting to database on page refresh\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Css handling of info modal and Tooltips (#418)\r\n\r\n* css change\r\n\r\n* toolTips\r\n\r\n* Sidebar Tooltips\r\n\r\n* copy to clip\r\n\r\n* css change\r\n\r\n* added image types\r\n\r\n* added gcs\r\n\r\n* type fix\r\n\r\n* docker changes\r\n\r\n* speech\r\n\r\n* added the toolip for dropzone sources\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed retrival bugs (#421)\r\n\r\n* yarn format fixes\r\n\r\n* changed the delete message\r\n\r\n* added the cancel  button\r\n\r\n* changed the message on tooltip\r\n\r\n* added space\r\n\r\n* UI fixes\r\n\r\n* tooltip for setting\r\n\r\n* updated req\r\n\r\n* wikipedia URL input (#424)\r\n\r\n* accept only wikipedia links\r\n\r\n* added wikipedia link\r\n\r\n* added wikilink regex\r\n\r\n* wikipedia single url only\r\n\r\n* changed the alert message\r\n\r\n* wording change\r\n\r\n* pushed validation state persist error\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* speech and copy (#422)\r\n\r\n* speech and copy\r\n\r\n* startTime\r\n\r\n* added chunk properties\r\n\r\n* tooltips\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* Fixed issue for out of range in KNN API\r\n\r\n* solved conflicts\r\n\r\n* conflict solved\r\n\r\n* Remove logging info from update KNN API\r\n\r\n* tooltip changes\r\n\r\n* format and lint fixes\r\n\r\n* responsiveness changes\r\n\r\n* Fixed issue for total pages GCS, S3\r\n\r\n* UI polishing (#428)\r\n\r\n* button and tooltip changes\r\n\r\n* checking validation on change\r\n\r\n* settings module populate fix\r\n\r\n* format fixes\r\n\r\n* opening the modal after auth success\r\n\r\n* removed the limit\r\n\r\n* added the scrobar for dropdowns\r\n\r\n* speech state (#426)\r\n\r\n* speech state\r\n\r\n* Button Details changes\r\n\r\n* delete wording change\r\n\r\n* Total pages in buckets (#431)\r\n\r\n* page number NA for buckets\r\n\r\n* added N/A for gcs and s3 pages\r\n\r\n* total pages for gcs\r\n\r\n* remove unwanted logger\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* removed the max width\r\n\r\n* Update FileTable.tsx\r\n\r\n* Update the docker file\r\n\r\n* Modified prompt (#438)\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* Update Dockerfile\r\n\r\n* rendering Fix\r\n\r\n* Local file upload gcs (#442)\r\n\r\n* Uplaod file to GCS\r\n\r\n* GCS local upload fixed issue and delete file from GCS after processing and failed or cancelled\r\n\r\n* Add life cycle rule on uploaded bucket\r\n\r\n* pdf upload local and gcs bucket check\r\n\r\n* delete files when processed and extract changes\r\n\r\n---------\r\n\r\nCo-authored-by: Pravesh Kumar <121786590+praveshkumar1988@users.noreply.github.com>\r\n\r\n* Modified chat length and entities used (#443)\r\n\r\n* metadata for unstructured files (#446)\r\n\r\n* Unstructured file metadata (#447)\r\n\r\n* metadata for unstructured files\r\n\r\n* sleep in gcs upload\r\n\r\n* updated\r\n\r\n* icons added to chunks (#435)\r\n\r\n* icons added to chunks\r\n\r\n* info modal icons\r\n\r\n* fixed gcs status message issue\r\n\r\n* added if check for failed count\r\n\r\n* Null issue Fixed from backend for upload API and graph_document when model name mismatch\r\n\r\n* added word break issue\r\n\r\n* Added neo4j-rust-ext\r\n\r\n* processing time estimation based on bytes\r\n\r\n* File extension upper case fixed, File delete from GCS or local based on env variable.\r\n\r\n* timer per byte\r\n\r\n* Update Dockerfile\r\n\r\n* Adding sort rows on the table (#451)\r\n\r\n* Gcs upload folder hashed (#453)\r\n\r\n* implement foldername hashed in GCS bucket uplaod\r\n\r\n* Raise exception if invalid model selected\r\n\r\n* folder name for gcs upload\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* upload all unstructuredfiles to gcs (#455)\r\n\r\n* Mofified chunk query (#454)\r\n\r\n* Added libre office for fixing error -- soffice command was not found. Please install libreoffice\r\non your system and try again.\r\n\r\n- Install instructions: https://www.libreoffice.org/get-help/install-howto/\r\n- Mac: https://formulae.brew.sh/cask/libreoffice\r\n- Debian: https://wiki.debian.org/LibreOffice\"\r\n\r\n* Fix the PARTIAL CONTENT issue\r\n\r\n* File-table no data found (#456)\r\n\r\n* 'file-table''\r\n\r\n* review comment\r\n\r\n* Llm format change (#459)\r\n\r\n* changed the llm models format to lowercase\r\n\r\n* added the error message\r\n\r\n* llm model changes\r\n\r\n* format fixes\r\n\r\n* removed unused import\r\n\r\n* added the capitalize method\r\n\r\n* delete files from merged_file_path only if source is local file\r\n\r\n---------\r\n\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\n\r\n* commented total page code (#460)\r\n\r\n* format fixes\r\n\r\n* removed the disabled check on dropdown\r\n\r\n* Large file env\r\n\r\n* added upload api\r\n\r\n* changed the dropzone error message\r\n\r\n---------\r\n\r\nCo-authored-by: abhishekkumar-27 <164544129+abhishekkumar-27@users.noreply.github.com>\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\nCo-authored-by: aashipandya <156318202+aashipandya@users.noreply.github.com>\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\nCo-authored-by: Prakriti Solankey <156313631+prakriti-solankey@users.noreply.github.com>\r\nCo-authored-by: Ajay Meena <meenajy1996@gmail.com>\r\nCo-authored-by: Morgan Senechal <morgan@neo4j.com>\r\nCo-authored-by: karanchellani <142801957+karanchellani@users.noreply.github.com>\r\n\r\n* format fixes\r\n\r\n* Close connect when graph object is not none\r\n\r\n* Call garbage collector to release the menory\r\n\r\n* Change error message\r\n\r\n* Added driver config as user_agent\r\n\r\n* Updated doc for the LLM_MODELS and GCS_FILE_CACHE (#473)\r\n\r\n* Web URLs are user input (#475)\r\n\r\n* web url support backend\r\n\r\n* added the tabs for input source\r\n\r\n* user agent added for Neo4jGraph connection\r\n\r\n* Tab view for sources\r\n\r\n* extract handling for web ur's\r\n\r\n* initial input handling\r\n\r\n* chunk creation before processing\r\n\r\n* code structure\r\n\r\n* format fixes\r\n\r\n---------\r\n\r\nCo-authored-by: kartikpersistent <101251502+kartikpersistent@users.noreply.github.com>\r\n\r\n* changed the regex for web and cancel button naming\r\n\r\n* changed the schema dropdown type\r\n\r\n* readme updates\r\n\r\n* PROD version fix\r\n\r\n* changed the alert message for gcs\r\n\r\n* Delete unconnected entities from DB (#482)\r\n\r\n* 457 add schema before generate graph (#478)\r\n\r\n* schema setting from generate graph\r\n\r\n* changes\r\n\r\n* changes\r\n\r\n* badge changes\r\n\r\n* bug fix\r\n\r\n* Fulltext index and Update similarity graph (#479)\r\n\r\n* added full_text index\r\n\r\n* added one common function for post_processing\r\n\r\n* post processing api\r\n\r\n* added tasks param\r\n\r\n* modifed logging\r\n\r\n* post processing changes\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\n\r\n* Graph and vector search (#485)\r\n\r\n* Modified the retrival query\r\n\r\n* added the chatmode toggle component\r\n\r\n* Modified to vector search\r\n\r\n* Moved the templates to constants\r\n\r\n* added the icons\r\n\r\n* added chat modes\r\n\r\n* code structure changes\r\n\r\n* Intergrated the API changges\r\n\r\n* Modified retrieval queries,refactored code\r\n\r\n* API integration changes\r\n\r\n* added the score\r\n\r\n* order change\r\n\r\n* wording change\r\n\r\n* modified constants\r\n\r\n* added graph+vector\r\n\r\n* added the tooltips\r\n\r\n* Modified query\r\n\r\n* removed the graph mode\r\n\r\n* tooltip camel Case\r\n\r\n* added the icon and extern link for web source in the info modal\r\n\r\n* added the youtube link in the source used tab\r\n\r\n* format fixes\r\n\r\n* added the hoverable link\r\n\r\n---------\r\n\r\nCo-authored-by: vasanthasaikalluri <165021735+vasanthasaikalluri@users.noreply.github.com>\r\n\r\n* Update InfoMo…","shortMessageHtmlLink":"DEV to STAGING (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2509819366\" data-permission-text=\"Title is private\" data-url=\"https://github.com/neo4j-labs/llm-graph-builder/issues/732\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/neo4j-labs/llm-graph-builder/pull/732/hovercard\" href=\"https://github.com/neo4j-labs/llm-graph-builder/pull/732\">#732</a>)"}},{"before":"4cc8104a0996c5d81ec8eb054d9439b0f8bb0528","after":"122f6a647247c257e859296cb11e3af7338334a4","ref":"refs/heads/DEV","pushedAt":"2024-09-06T09:07:00.000Z","pushType":"push","commitsCount":17,"pusher":{"login":"aashipandya","name":null,"path":"/aashipandya","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/156318202?s=80&v=4"},"commit":{"message":"Merge branch 'STAGING' into DEV","shortMessageHtmlLink":"Merge branch 'STAGING' into DEV"}},{"before":"ba131448d313e97e7d6fe8816a230ad4096ebb33","after":"4cc8104a0996c5d81ec8eb054d9439b0f8bb0528","ref":"refs/heads/DEV","pushedAt":"2024-09-06T07:46:56.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"praveshkumar1988","name":"Pravesh Kumar","path":"/praveshkumar1988","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/121786590?s=80&v=4"},"commit":{"message":"Add vector index exist condition to create","shortMessageHtmlLink":"Add vector index exist condition to create"}},{"before":"949d2f9b62f41da53a26caa921a889785a09436f","after":"ba131448d313e97e7d6fe8816a230ad4096ebb33","ref":"refs/heads/DEV","pushedAt":"2024-09-06T06:36:41.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"kartikpersistent","name":null,"path":"/kartikpersistent","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/101251502?s=80&v=4"},"commit":{"message":"resetting the nodescount and relationshipcount","shortMessageHtmlLink":"resetting the nodescount and relationshipcount"}},{"before":"c91febba99224ef963065f059f46835165d120ce","after":"169c2727820ea0469c88bf6ccfa10a46617442fe","ref":"refs/heads/communities","pushedAt":"2024-09-05T16:36:44.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vasanthasaikalluri","name":null,"path":"/vasanthasaikalluri","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/165021735?s=80&v=4"},"commit":{"message":"modified constants","shortMessageHtmlLink":"modified constants"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEslDegwA","startCursor":null,"endCursor":null}},"title":"Activity · neo4j-labs/llm-graph-builder"}