core: Add additional properties recursively for structured output(openai) when nested object is generated

[fufufukakaka]

Hello.
First of all, thank you for maintaining such a great project.

Description

In #25123, support for structured_output is added. However, "additionalProperties": false needs to be included at all levels when a nested object is generated.

error from current code: https://gist.github.com/fufufukakaka/e9b475300e6934853d119428e390f204

BadRequestError: Error code: 400 - {'error': {'message': "Invalid schema for response_format 'JokeWithEvaluation': In context=('properties', 'self_evaluation'), 'additionalProperties' is required to be supplied and to be false", 'type': 'invalid_request_error', 'param': 'response_format', 'code': None}}

Reference: Introducing Structured Outputs in the API

{
  "model": "gpt-4o-2024-08-06",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful math tutor."
    },
    {
      "role": "user",
      "content": "solve 8x + 31 = 2"
    }
  ],
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "name": "math_response",
      "strict": true,
      "schema": {
        "type": "object",
        "properties": {
          "steps": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "explanation": {
                  "type": "string"
                },
                "output": {
                  "type": "string"
                }
              },
              "required": ["explanation", "output"],
              "additionalProperties": false
            }
          },
          "final_answer": {
            "type": "string"
          }
        },
        "required": ["steps", "final_answer"],
        "additionalProperties": false
      }
    }
  }
}

In the current code, "additionalProperties": false is only added at the last level.
This PR introduces the _add_additional_properties_key function, which recursively adds "additionalProperties": false to the entire JSON schema for the request.

Twitter handle: @fukkaa1225

Thank you!

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Skipped Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchain	⬜️ Ignored (Inspect)	Visit Preview		Aug 23, 2024 0:05am

[fufufukakaka]

now, pydantic outputs json schema includes 'allOf', but openai don't support.
pydantic PR → pydantic/pydantic#10029

BadRequestError: Error code: 400 - {'error': {'message': "Invalid schema for response_format 'JokeWithEvaluation': In context=('properties', 'self_evaluation'), 'allOf' is not permitted", 'type': 'invalid_request_error', 'param': 'response_format', 'code': None}}

full error: https://gist.github.com/fufufukakaka/0f638b40687a00fc712819f7b3dd0b5e

So, I'll only implement tests using TypedDict. 🙏

[sajal2692]

When is this expected to be merged? would be super useful

[baskaryan]

could we add unit tests for this functionality instead of integration tests?

[baskaryan]

thank you @fufufukakaka! will be out in langchain-core 0.2.35, which will be released later today

[fufufukakaka]

thanks!