github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-19 05:13:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: anthropic api ref nit (#26591)

Browse Source
This commit is contained in:
Bagatur 2024-09-17 13:39:53 -07:00 committed by GitHub
parent e1d113ea84
commit 97b05d70e6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 25 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
libs/partners/anthropic/langchain_anthropic/chat_models.py
View File

@ -807,14 +807,14 @@ class ChatAnthropic(BaseChatModel):
Args: Args:
tools: A list of tool definitions to bind to this chat model. tools: A list of tool definitions to bind to this chat model.
Supports Anthropic format tool schemas and any tool definition handled Supports Anthropic format tool schemas and any tool definition handled
by :meth:`langchain_core.utils.function_calling.convert_to_openai_tool`. by :meth:`~langchain_core.utils.function_calling.convert_to_openai_tool`.
tool_choice: Which tool to require the model to call. Options are: tool_choice: Which tool to require the model to call. Options are:
- name of the tool as a string or as dict ``{"type": "tool", "name": "<<tool_name>>"}``: calls corresponding tool; - name of the tool as a string or as dict ``{"type": "tool", "name": "<<tool_name>>"}``: calls corresponding tool;
- ``"auto"``, ``{"type: "auto"}``, or None: automatically selects a tool (including no tool); - ``"auto"``, ``{"type: "auto"}``, or None: automatically selects a tool (including no tool);
- ``"any"`` or ``{"type: "any"}``: force at least one tool to be called; - ``"any"`` or ``{"type: "any"}``: force at least one tool to be called;
kwargs: Any additional parameters are passed directly to kwargs: Any additional parameters are passed directly to
``self.bind(**kwargs)``. :meth:`~langchain_anthropic.chat_models.ChatAnthropic.bind`.
Example: Example:
.. code-block:: python .. code-block:: python
@ -833,7 +833,7 @@ class ChatAnthropic(BaseChatModel):
product: str = Field(..., description="The product to look up.") product: str = Field(..., description="The product to look up.")
llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0) llm = ChatAnthropic(model="claude-3-5-sonnet-20240620", temperature=0)
llm_with_tools = llm.bind_tools([GetWeather, GetPrice]) llm_with_tools = llm.bind_tools([GetWeather, GetPrice])
llm_with_tools.invoke("what is the weather like in San Francisco",) llm_with_tools.invoke("what is the weather like in San Francisco",)
# -> AIMessage( # -> AIMessage(
@ -841,7 +841,7 @@ class ChatAnthropic(BaseChatModel):
# {'text': '<thinking>\nBased on the user\'s question, the relevant function to call is GetWeather, which requires the "location" parameter.\n\nThe user has directly specified the location as "San Francisco". Since San Francisco is a well known city, I can reasonably infer they mean San Francisco, CA without needing the state specified.\n\nAll the required parameters are provided, so I can proceed with the API call.\n</thinking>', 'type': 'text'}, # {'text': '<thinking>\nBased on the user\'s question, the relevant function to call is GetWeather, which requires the "location" parameter.\n\nThe user has directly specified the location as "San Francisco". Since San Francisco is a well known city, I can reasonably infer they mean San Francisco, CA without needing the state specified.\n\nAll the required parameters are provided, so I can proceed with the API call.\n</thinking>', 'type': 'text'},
# {'text': None, 'type': 'tool_use', 'id': 'toolu_01SCgExKzQ7eqSkMHfygvYuu', 'name': 'GetWeather', 'input': {'location': 'San Francisco, CA'}} # {'text': None, 'type': 'tool_use', 'id': 'toolu_01SCgExKzQ7eqSkMHfygvYuu', 'name': 'GetWeather', 'input': {'location': 'San Francisco, CA'}}
# ], # ],
# response_metadata={'id': 'msg_01GM3zQtoFv8jGQMW7abLnhi', 'model': 'claude-3-opus-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 487, 'output_tokens': 145}}, # response_metadata={'id': 'msg_01GM3zQtoFv8jGQMW7abLnhi', 'model': 'claude-3-5-sonnet-20240620', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 487, 'output_tokens': 145}},
# id='run-87b1331e-9251-4a68-acef-f0a018b639cc-0' # id='run-87b1331e-9251-4a68-acef-f0a018b639cc-0'
# ) # )
@ -862,7 +862,7 @@ class ChatAnthropic(BaseChatModel):
product: str = Field(..., description="The product to look up.") product: str = Field(..., description="The product to look up.")
llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0) llm = ChatAnthropic(model="claude-3-5-sonnet-20240620", temperature=0)
llm_with_tools = llm.bind_tools([GetWeather, GetPrice], tool_choice="any") llm_with_tools = llm.bind_tools([GetWeather, GetPrice], tool_choice="any")
llm_with_tools.invoke("what is the weather like in San Francisco",) llm_with_tools.invoke("what is the weather like in San Francisco",)
@ -884,7 +884,7 @@ class ChatAnthropic(BaseChatModel):
product: str = Field(..., description="The product to look up.") product: str = Field(..., description="The product to look up.")
llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0) llm = ChatAnthropic(model="claude-3-5-sonnet-20240620", temperature=0)
llm_with_tools = llm.bind_tools([GetWeather, GetPrice], tool_choice="GetWeather") llm_with_tools = llm.bind_tools([GetWeather, GetPrice], tool_choice="GetWeather")
llm_with_tools.invoke("what is the weather like in San Francisco",) llm_with_tools.invoke("what is the weather like in San Francisco",)
@ -915,7 +915,7 @@ class ChatAnthropic(BaseChatModel):
# We need to pass in extra headers to enable use of the beta cache # We need to pass in extra headers to enable use of the beta cache
# control API. # control API.
llm = ChatAnthropic( llm = ChatAnthropic(
model="claude-3-opus-20240229", model="claude-3-5-sonnet-20240620",
temperature=0, temperature=0,
extra_headers={"anthropic-beta": "prompt-caching-2024-07-31"} extra_headers={"anthropic-beta": "prompt-caching-2024-07-31"}
) )
@ -961,24 +961,20 @@ class ChatAnthropic(BaseChatModel):
"""Model wrapper that returns outputs formatted to match the given schema. """Model wrapper that returns outputs formatted to match the given schema.
Args: Args:
schema: schema: The output schema. Can be passed in as:
The output schema. Can be passed in as:
- an Anthropic tool schema, - an Anthropic tool schema,
- an OpenAI function/tool schema, - an OpenAI function/tool schema,
- a JSON Schema, - a JSON Schema,
- a TypedDict class (support added in 0.1.22), - a TypedDict class,
- or a Pydantic class. - or a Pydantic class.
If ``schema`` is a Pydantic class then the model output will be a If ``schema`` is a Pydantic class then the model output will be a
Pydantic instance of that class, and the model-generated fields will be Pydantic instance of that class, and the model-generated fields will be
validated by the Pydantic class. Otherwise the model output will be a validated by the Pydantic class. Otherwise the model output will be a
dict and will not be validated. See :meth:`langchain_core.utils.function_calling.convert_to_openai_tool` dict and will not be validated. See :meth:`~langchain_core.utils.function_calling.convert_to_openai_tool`
for more on how to properly specify types and descriptions of for more on how to properly specify types and descriptions of
schema fields when specifying a Pydantic or TypedDict class. schema fields when specifying a Pydantic or TypedDict class.
.. versionchanged:: 0.1.22
Added support for TypedDict class.
include_raw: include_raw:
If False then only the parsed structured output is returned. If If False then only the parsed structured output is returned. If
an error occurs during model output parsing it will be raised. If True an error occurs during model output parsing it will be raised. If True
@ -986,9 +982,10 @@ class ChatAnthropic(BaseChatModel):
response will be returned. If an error occurs during output parsing it response will be returned. If an error occurs during output parsing it
will be caught and returned as well. The final output is always a dict will be caught and returned as well. The final output is always a dict
with keys "raw", "parsed", and "parsing_error". with keys "raw", "parsed", and "parsing_error".
kwargs: Additional keyword arguments are ignored.
Returns: Returns:
A Runnable that takes same inputs as a :class:`langchain_core.language_models.chat.BaseChatModel`. A Runnable that takes same inputs as a :class:`~langchain_core.language_models.chat.BaseChatModel`.
If ``include_raw`` is False and ``schema`` is a Pydantic class, Runnable outputs If ``include_raw`` is False and ``schema`` is a Pydantic class, Runnable outputs
an instance of ``schema`` (i.e., a Pydantic object). an instance of ``schema`` (i.e., a Pydantic object).
@ -1011,7 +1008,7 @@ class ChatAnthropic(BaseChatModel):
answer: str answer: str
justification: str justification: str
llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0) llm = ChatAnthropic(model="claude-3-5-sonnet-20240620", temperature=0)
structured_llm = llm.with_structured_output(AnswerWithJustification) structured_llm = llm.with_structured_output(AnswerWithJustification)
structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers") structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
@ -1032,7 +1029,7 @@ class ChatAnthropic(BaseChatModel):
answer: str answer: str
justification: str justification: str
llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0) llm = ChatAnthropic(model="claude-3-5-sonnet-20240620", temperature=0)
structured_llm = llm.with_structured_output(AnswerWithJustification, include_raw=True) structured_llm = llm.with_structured_output(AnswerWithJustification, include_raw=True)
structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers") structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
@ -1059,7 +1056,7 @@ class ChatAnthropic(BaseChatModel):
"required": ["answer", "justification"] "required": ["answer", "justification"]
} }
} }
llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0) llm = ChatAnthropic(model="claude-3-5-sonnet-20240620", temperature=0)
structured_llm = llm.with_structured_output(schema) structured_llm = llm.with_structured_output(schema)
structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers") structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
@ -1068,6 +1065,10 @@ class ChatAnthropic(BaseChatModel):
# 'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.' # 'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume and density of the two substances differ.'
# } # }
.. versionchanged:: 0.1.22
Added support for TypedDict class as `schema`.
""" # noqa: E501 """ # noqa: E501
tool_name = convert_to_anthropic_tool(schema)["name"] tool_name = convert_to_anthropic_tool(schema)["name"]