vectara-agentic

Overview

vectara-agentic is a Python library for developing powerful AI assistants using Vectara and Agentic-RAG. It leverages the LlamaIndex Agent framework, customized for use with Vectara.

Key Features

• Supports ReAct and OpenAIAgent agent types.
• Includes pre-built tools for various domains (e.g., finance, legal).
• Enables easy creation of custom AI assistants and agents.

Important Links

• Documentation: https://vectara.github.io/vectara-agentic-docs/

Prerequisites

• Vectara account
• A Vectara corpus with an API key
• Python 3.10 or higher
• OpenAI API key (or API keys for Anthropic, TOGETHER.AI, Fireworks AI, or GROQ)

Installation

pip install vectara-agentic

Quick Start

1. Create a Vectara RAG tool

import os
from vectara_agentic import VectaraToolFactory

vec_factory = VectaraToolFactory(
    vectara_api_key=os.environ['VECTARA_API_KEY'],
    vectara_customer_id=os.environ['VECTARA_CUSTOMER_ID'],
    vectara_corpus_id=os.environ['VECTARA_CORPUS_ID']
)

query_financial_reports = vec_factory.create_rag_tool(
    tool_name="query_financial_reports",
    tool_description="Query financial reports for a company and year",
    tool_args_schema=QueryFinancialReportsArgs,
    tool_filter_template="doc.year = {year} and doc.ticker = '{ticker}'"
)

2. Create other tools (optional)

In addition to RAG tools, you can generate a lot of other types of tools the agent can use. These could be mathematical tools, tools that call other APIs to get more information, or any other type of tool.

See Tools for more information.

3. Create your agent

agent = Agent(
    tools = [query_financial_reports],
    topic = topic_of_expertise,
    custom_instructions = financial_bot_instructions,
)

• tools is the list of tools you want to provide to the agent. In this example it's just a single tool.
• topic is a string that defines the expertise you want the agent to specialize in.
• custom_instructions is an optional string that defines special instructions to the agent.

For example, for a financial agent we might use:

topic_of_expertise = "10-K financial reports",

financial_bot_instructions = """
    - You are a helpful financial assistant in conversation with a user. Use your financial expertise when crafting a query to the tool, to ensure you get the most accurate information.
    - You can answer questions, provide insights, or summarize any information from financial reports.
    - A user may refer to a company's ticker instead of its full name - consider those the same when a user is asking about a company.
    - When calculating a financial metric, make sure you have all the information from tools to complete the calculation.
    - In many cases you may need to query tools on each sub-metric separately before computing the final metric.
    - When using a tool to obtain financial data, consider the fact that information for a certain year may be reported in the the following year's report.
    - Report financial data in a consistent manner. For example if you report revenue in thousands, always report revenue in thousands.
    """

Configuration

Configure vectara-agentic using environment variables:

• VECTARA_AGENTIC_AGENT_TYPE: valid values are REACT or OPENAI (default: OPENAI)
• VECTARA_AGENTIC_MAIN_LLM_PROVIDER: valid values are OPENAI, ANTHROPIC, TOGETHER, GROQ, or FIREWORKS (default: OPENAI)
• VECTARA_AGENTIC_MAIN_MODEL_NAME: agent model name (default depends on provider)
• VECTARA_AGENTIC_TOOL_LLM_PROVIDER: tool LLM provider (default: OPENAI)
• VECTARA_AGENTIC_TOOL_MODEL_NAME: tool model name (default depends on provider)

Agent Tools

vectara-agentic provides a few tools out of the box:

1. Standard tools:

• summarize_text: a tool to summarize a long text into a shorter summary (uses LLM)
• rephrase_text: a tool to rephrase a given text, given a set of rephrase instructions (uses LLM)

2. Legal tools: a set of tools for the legal vertical, such as:

• summarize_legal_text: summarize legal text with a certain point of view
• critique_as_judge: critique a legal text as a judge, providing their perspective

3. Financial tools: based on tools from Yahoo Finance:

• tools to understand the financials of a public company like: balance_sheet, income_statement, cash_flow
• stock_news: provides news about a company
• stock_analyst_recommendations: provides stock analyst recommendations for a company.

4. database_tools: providing a few tools to inspect and query a database

• list_tables: list all tables in the database
• describe_tables: describe the schema of tables in the database
• load_data: returns data based on a SQL query

More tools coming soon.

You can create your own tool directly from a Python function using the create_tool() method of the ToolsFactor class:

def mult_func(x, y):
    return x*y

mult_tool = ToolsFactory().create_tool(mult_func)

Examples

Check out our example AI assistants:

• Financial Assistant
• Justice Harvard Teaching Assistant
• Legal Assistant

Contributing

We welcome contributions! Please see our contributing guide for more information.

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.

Contact

• Website: vectara.com
• Twitter: @vectara
• GitHub: @vectara
• LinkedIn: @vectara
• Discord: Join our community