community: add bind_tools and with_structured_output support to QianfanChatEndpoint (#21412)

…Endpoint`

Thank you for contributing to LangChain!

- [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:** add `bind_tools` and `with_structured_output` support
to `QianfanChatEndpoint`


- [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/

libs/community/langchain_community/chat_models/baidu_qianfan_endpoint.py

@@ -1,10 +1,25 @@
 import logging
-from typing import Any, AsyncIterator, Dict, Iterator, List, Mapping, Optional, cast
+from operator import itemgetter
+from typing import (
+    Any,
+    AsyncIterator,
+    Callable,
+    Dict,
+    Iterator,
+    List,
+    Mapping,
+    Optional,
+    Sequence,
+    Type,
+    Union,
+    cast,
+)
 
 from langchain_core.callbacks import (
     AsyncCallbackManagerForLLMRun,
     CallbackManagerForLLMRun,
 )
+from langchain_core.language_models import LanguageModelInput
 from langchain_core.language_models.chat_models import BaseChatModel
 from langchain_core.messages import (
     AIMessage,
@@ -15,9 +30,17 @@ from langchain_core.messages import (
     HumanMessage,
     SystemMessage,
 )
+from langchain_core.output_parsers.base import OutputParserLike
+from langchain_core.output_parsers.openai_tools import (
+    JsonOutputKeyToolsParser,
+    PydanticToolsParser,
+)
 from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, ChatResult
-from langchain_core.pydantic_v1 import Field, SecretStr, root_validator
+from langchain_core.pydantic_v1 import BaseModel, Field, SecretStr, root_validator
+from langchain_core.runnables import Runnable, RunnableMap, RunnablePassthrough
+from langchain_core.tools import BaseTool
 from langchain_core.utils import convert_to_secret_str, get_from_dict_or_env
+from langchain_core.utils.function_calling import convert_to_openai_tool
 
 logger = logging.getLogger(__name__)
 
@@ -66,6 +89,12 @@ def _convert_dict_to_message(_dict: Mapping[str, Any]) -> AIMessage:
             object=additional_kwargs.get("object", ""),
             search_info=additional_kwargs.get("search_info", []),
             function_call=additional_kwargs.get("function_call", {}),
+            tool_calls=[
+                {
+                    "type": "function",
+                    "function": additional_kwargs.get("function_call", {}),
+                }
+            ],
         ),
     )
 
@@ -391,3 +420,154 @@ class QianfanChatEndpoint(BaseChatModel):
                 if run_manager:
                     await run_manager.on_llm_new_token(chunk.text, chunk=chunk)
                 yield chunk
+
+    def bind_tools(
+        self,
+        tools: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable, BaseTool]],
+        **kwargs: Any,
+    ) -> Runnable[LanguageModelInput, BaseMessage]:
+        """Bind tool-like objects to this chat model.
+
+        Assumes model is compatible with OpenAI tool-calling API.
+
+        Args:
+            tools: A list of tool definitions to bind to this chat model.
+                Can be  a dictionary, pydantic model, callable, or BaseTool. Pydantic
+                models, callables, and BaseTools will be automatically converted to
+                their schema dictionary representation.
+            **kwargs: Any additional parameters to pass to the
+                :class:`~langchain.runnable.Runnable` constructor.
+        """
+
+        formatted_tools = [convert_to_openai_tool(tool)["function"] for tool in tools]
+        return super().bind(functions=formatted_tools, **kwargs)
+
+    def with_structured_output(
+        self,
+        schema: Union[Dict, Type[BaseModel]],
+        *,
+        include_raw: bool = False,
+        **kwargs: Any,
+    ) -> Runnable[LanguageModelInput, Union[Dict, BaseModel]]:
+        """Model wrapper that returns outputs formatted to match the given schema.
+
+        Args:
+            schema: The output schema as a dict or a Pydantic class. If a Pydantic class
+                then the model output will be an object of that class. If a dict then
+                the model output will be a dict. With a Pydantic class the returned
+                attributes will be validated, whereas with a dict they will not be. If
+                `method` is "function_calling" and `schema` is a dict, then the dict
+                must match the OpenAI function-calling spec.
+            include_raw: If False then only the parsed structured output is returned. If
+                an error occurs during model output parsing it will be raised. If True
+                then both the raw model response (a BaseMessage) and the parsed model
+                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
+                with keys "raw", "parsed", and "parsing_error".
+
+        Returns:
+            A Runnable that takes any ChatModel input and returns as output:
+
+                If include_raw is True then a dict with keys:
+                    raw: BaseMessage
+                    parsed: Optional[_DictOrPydantic]
+                    parsing_error: Optional[BaseException]
+
+                If include_raw is False then just _DictOrPydantic is returned,
+                where _DictOrPydantic depends on the schema:
+
+                If schema is a Pydantic class then _DictOrPydantic is the Pydantic
+                    class.
+
+                If schema is a dict then _DictOrPydantic is a dict.
+
+        Example: Function-calling, Pydantic schema (method="function_calling", include_raw=False):
+            .. code-block:: python
+
+                from langchain_mistralai import QianfanChatEndpoint
+                from langchain_core.pydantic_v1 import BaseModel
+
+                class AnswerWithJustification(BaseModel):
+                    '''An answer to the user question along with justification for the answer.'''
+                    answer: str
+                    justification: str
+
+                llm = QianfanChatEndpoint(endpoint="ernie-3.5-8k-0329")
+                structured_llm = llm.with_structured_output(AnswerWithJustification)
+
+                structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+
+                # -> AnswerWithJustification(
+                #     answer='They weigh the same',
+                #     justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'
+                # )
+
+        Example: Function-calling, Pydantic schema (method="function_calling", include_raw=True):
+            .. code-block:: python
+
+                from langchain_mistralai import QianfanChatEndpoint
+                from langchain_core.pydantic_v1 import BaseModel
+
+                class AnswerWithJustification(BaseModel):
+                    '''An answer to the user question along with justification for the answer.'''
+                    answer: str
+                    justification: str
+
+                llm = QianfanChatEndpoint(endpoint="ernie-3.5-8k-0329")
+                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")
+                # -> {
+                #     'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_Ao02pnFYXD6GN1yzc0uXPsvF', 'function': {'arguments': '{"answer":"They weigh the same.","justification":"Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ."}', 'name': 'AnswerWithJustification'}, 'type': 'function'}]}),
+                #     'parsed': AnswerWithJustification(answer='They weigh the same.', justification='Both a pound of bricks and a pound of feathers weigh one pound. The weight is the same, but the volume or density of the objects may differ.'),
+                #     'parsing_error': None
+                # }
+
+        Example: Function-calling, dict schema (method="function_calling", include_raw=False):
+            .. code-block:: python
+
+                from langchain_mistralai import QianfanChatEndpoint
+                from langchain_core.pydantic_v1 import BaseModel
+                from langchain_core.utils.function_calling import convert_to_openai_tool
+
+                class AnswerWithJustification(BaseModel):
+                    '''An answer to the user question along with justification for the answer.'''
+                    answer: str
+                    justification: str
+
+                dict_schema = convert_to_openai_tool(AnswerWithJustification)
+                llm = QianfanChatEndpoint(endpoint="ernie-3.5-8k-0329")
+                structured_llm = llm.with_structured_output(dict_schema)
+
+                structured_llm.invoke("What weighs more a pound of bricks or a pound of feathers")
+                # -> {
+                #     'answer': 'They weigh the same',
+                #     '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.'
+                # }
+
+        """  # noqa: E501
+        if kwargs:
+            raise ValueError(f"Received unsupported arguments {kwargs}")
+        is_pydantic_schema = isinstance(schema, type) and issubclass(schema, BaseModel)
+        llm = self.bind_tools([schema])
+        if is_pydantic_schema:
+            output_parser: OutputParserLike = PydanticToolsParser(
+                tools=[schema], first_tool_only=True
+            )
+        else:
+            key_name = convert_to_openai_tool(schema)["function"]["name"]
+            output_parser = JsonOutputKeyToolsParser(
+                key_name=key_name, first_tool_only=True
+            )
+
+        if include_raw:
+            parser_assign = RunnablePassthrough.assign(
+                parsed=itemgetter("raw") | output_parser, parsing_error=lambda _: None
+            )
+            parser_none = RunnablePassthrough.assign(parsed=lambda _: None)
+            parser_with_fallback = parser_assign.with_fallbacks(
+                [parser_none], exception_key="parsing_error"
+            )
+            return RunnableMap(raw=llm) | parser_with_fallback
+        else:
+            return llm | output_parser