core: update _rm_titles to account for title argument name bug (#19036)

Issue : For functions which have an argument with the name 'title', the
convert_pydantic_to_openai_function generates an incorrect output and
omits the argument all together. This is because the _rm_titles function
removes all instances of the the key 'title' from the output.



Description : Updates the _rm_titles function to check the presence of
the 'type' key as well before removing the 'title' key. As the title key
that we wish to omit always has a type key along with it.

Potential gap if there is a function defined which has both title and
key as argument names, in which case this would fail. Maybe we could set
a filter on the function argument names and reject those with keyword
argument names.


No dependencies. Passed all tests. 


- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [x] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [x] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.


- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
This commit is contained in:
Roshan Santhosh 2024-03-18 21:25:06 -07:00 committed by GitHub
parent efcdf54edd
commit 7afecec280
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 206 additions and 3 deletions

View File

@ -1,4 +1,5 @@
"""Methods for creating function specs in the style of OpenAI Functions"""
from __future__ import annotations
import inspect
@ -51,13 +52,16 @@ class ToolDescription(TypedDict):
function: FunctionDescription
def _rm_titles(kv: dict) -> dict:
def _rm_titles(kv: dict, prev_key: str = "") -> dict:
new_kv = {}
for k, v in kv.items():
if k == "title":
continue
if isinstance(v, dict) and prev_key == "properties" and "title" in v.keys():
new_kv[k] = _rm_titles(v, k)
else:
continue
elif isinstance(v, dict):
new_kv[k] = _rm_titles(v)
new_kv[k] = _rm_titles(v, k)
else:
new_kv[k] = v
return new_kv

View File

@ -0,0 +1,199 @@
import pytest
from langchain_core.utils.function_calling import _rm_titles
output1 = {
"type": "object",
"properties": {
"people": {
"description": "List of info about people",
"type": "array",
"items": {
"description": "Information about a person.",
"type": "object",
"properties": {
"name": {"type": "string"},
"title": {"description": "person's age", "type": "integer"},
},
"required": ["name"],
},
}
},
"required": ["people"],
}
schema1 = {
"type": "object",
"properties": {
"people": {
"title": "People",
"description": "List of info about people",
"type": "array",
"items": {
"title": "Person",
"description": "Information about a person.",
"type": "object",
"properties": {
"name": {"title": "Name", "type": "string"},
"title": {
"title": "Title",
"description": "person's age",
"type": "integer",
},
},
"required": ["name"],
},
}
},
"required": ["people"],
}
output2 = {
"type": "object",
"properties": {
"title": {
"description": "List of info about people",
"type": "array",
"items": {
"description": "Information about a person.",
"type": "object",
"properties": {
"name": {"type": "string"},
"age": {"description": "person's age", "type": "integer"},
},
"required": ["name"],
},
}
},
"required": ["title"],
}
schema2 = {
"type": "object",
"properties": {
"title": {
"title": "Title",
"description": "List of info about people",
"type": "array",
"items": {
"title": "Person",
"description": "Information about a person.",
"type": "object",
"properties": {
"name": {"title": "Name", "type": "string"},
"age": {
"title": "Age",
"description": "person's age",
"type": "integer",
},
},
"required": ["name"],
},
}
},
"required": ["title"],
}
output3 = {
"type": "object",
"properties": {
"title": {
"description": "List of info about people",
"type": "array",
"items": {
"description": "Information about a person.",
"type": "object",
"properties": {
"title": {"type": "string"},
"type": {"description": "person's age", "type": "integer"},
},
"required": ["title"],
},
}
},
"required": ["title"],
}
schema3 = {
"type": "object",
"properties": {
"title": {
"title": "Title",
"description": "List of info about people",
"type": "array",
"items": {
"title": "Person",
"description": "Information about a person.",
"type": "object",
"properties": {
"title": {"title": "Title", "type": "string"},
"type": {
"title": "Type",
"description": "person's age",
"type": "integer",
},
},
"required": ["title"],
},
}
},
"required": ["title"],
}
output4 = {
"type": "object",
"properties": {
"properties": {
"description": "Information to extract",
"type": "object",
"properties": {
"title": {
"description": "Information about papers mentioned.",
"type": "object",
"properties": {
"title": {"type": "string"},
"author": {"type": "string"},
},
"required": ["title"],
}
},
"required": ["title"],
}
},
"required": ["properties"],
}
schema4 = {
"type": "object",
"properties": {
"properties": {
"title": "Info",
"description": "Information to extract",
"type": "object",
"properties": {
"title": {
"title": "Paper",
"description": "Information about papers mentioned.",
"type": "object",
"properties": {
"title": {"title": "Title", "type": "string"},
"author": {"title": "Author", "type": "string"},
},
"required": ["title"],
}
},
"required": ["title"],
}
},
"required": ["properties"],
}
@pytest.mark.parametrize(
"schema, output",
[(schema1, output1), (schema2, output2), (schema3, output3), (schema4, output4)],
)
def test_rm_titles(schema: dict, output: dict) -> None:
assert _rm_titles(schema) == output