a ag, @sddlmZddlZddlmZddlmZmZmZm Z m Z m Z m Z m Z mZmZmZmZmZmZddlmZmZmZddlmZmZddlmZmZddlmZm Z m!Z!dd l"m#Z#dd l$m%Z%dd l&m'Z'm(Z(dd l)m*Z*dd l+m,Z,gdZ-edddddddddddddZ.ed6dddddddddddddZ.ed7dddddddddddddZ.d8dddddddddddddZ.dd ddddd!d"d#Z/hd$Z0ddd%d&d'Z1ddd(d)d*d+Z2dd,ddd-d.d/d0Z3dddd1d2d3Z4d4Z5Gd5ddeeefZ6dS)9) annotationsN)util)Any AsyncIteratorCallableDictIteratorListLiteralOptionalSequenceTupleTypeUnioncastoverload) BaseChatModelLanguageModelInputSimpleChatModel)agenerate_from_streamgenerate_from_stream) AnyMessage BaseMessage)RunnableRunnableConfig ensure_config) StreamEvent)BaseTool)RunLog RunLogPatch) BaseModel) TypeAlias)init_chat_modelrrrr)model_providerconfigurable_fields config_prefixstrz Optional[str]z Literal[None]rr)modelr#r$r%kwargsreturncKsdSNr'r#r$r%r(r+r+h/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain/chat_models/base.pyr"1sr"_ConfigurableModelcKsdSr*r+r,r+r+r-r"<s.1Union[Literal['any'], List[str], Tuple[str, ...]]cKsdSr*r+r,r+r+r-r"Gsz;Optional[Union[Literal['any'], List[str], Tuple[str, ...]]]z(Union[BaseChatModel, _ConfigurableModel]cKsv|s |s d}|pd}|r.|s.td|d|sLttt|fd|i|S|rX||d<|rd||d<t|||dSdS) aP#Initialize a ChatModel from the model name and provider. **Note:** Must have the integration package corresponding to the model provider installed. Args: model: The name of the model, e.g. "gpt-4o", "claude-3-opus-20240229". model_provider: The model provider. Supported model_provider values and the corresponding integration package are: - 'openai' -> langchain-openai - 'anthropic' -> langchain-anthropic - 'azure_openai' -> langchain-openai - 'google_vertexai' -> langchain-google-vertexai - 'google_genai' -> langchain-google-genai - 'bedrock' -> langchain-aws - 'bedrock_converse' -> langchain-aws - 'cohere' -> langchain-cohere - 'fireworks' -> langchain-fireworks - 'together' -> langchain-together - 'mistralai' -> langchain-mistralai - 'huggingface' -> langchain-huggingface - 'groq' -> langchain-groq - 'ollama' -> langchain-ollama - 'google_anthropic_vertex' -> langchain-google-vertexai Will attempt to infer model_provider from model if not specified. The following providers will be inferred based on these model prefixes: - 'gpt-3...' | 'gpt-4...' | 'o1...' -> 'openai' - 'claude...' -> 'anthropic' - 'amazon....' -> 'bedrock' - 'gemini...' -> 'google_vertexai' - 'command...' -> 'cohere' - 'accounts/fireworks...' -> 'fireworks' - 'mistral...' -> 'mistralai' configurable_fields: Which model parameters are configurable: - None: No configurable fields. - "any": All fields are configurable. *See Security Note below.* - Union[List[str], Tuple[str, ...]]: Specified fields are configurable. Fields are assumed to have config_prefix stripped if there is a config_prefix. If model is specified, then defaults to None. If model is not specified, then defaults to ``("model", "model_provider")``. ***Security Note***: Setting ``configurable_fields="any"`` means fields like api_key, base_url, etc. can be altered at runtime, potentially redirecting model requests to a different service/user. Make sure that if you're accepting untrusted configurations that you enumerate the ``configurable_fields=(...)`` explicitly. config_prefix: If config_prefix is a non-empty string then model will be configurable at runtime via the ``config["configurable"]["{config_prefix}_{param}"]`` keys. If config_prefix is an empty string then model will be configurable via ``config["configurable"]["{param}"]``. temperature: Model temperature. max_tokens: Max output tokens. timeout: The maximum time (in seconds) to wait for a response from the model before canceling the request. max_retries: The maximum number of attempts the system will make to resend a request if it fails due to issues like network timeouts or rate limits. base_url: The URL of the API endpoint where requests are sent. rate_limiter: A ``BaseRateLimiter`` to space out requests to avoid exceeding rate limits. kwargs: Additional model-specific keyword args to pass to ``<>.__init__(model=model_name, **kwargs)``. Returns: A BaseChatModel corresponding to the model_name and model_provider specified if configurability is inferred to be False. If configurable, a chat model emulator that initializes the underlying model at runtime once a config is passed in. Raises: ValueError: If model_provider cannot be inferred or isn't supported. ImportError: If the model provider integration package is not installed. .. dropdown:: Init non-configurable model :open: .. code-block:: python # pip install langchain langchain-openai langchain-anthropic langchain-google-vertexai from langchain.chat_models import init_chat_model gpt_4o = init_chat_model("gpt-4o", model_provider="openai", temperature=0) claude_opus = init_chat_model("claude-3-opus-20240229", model_provider="anthropic", temperature=0) gemini_15 = init_chat_model("gemini-1.5-pro", model_provider="google_vertexai", temperature=0) gpt_4o.invoke("what's your name") claude_opus.invoke("what's your name") gemini_15.invoke("what's your name") .. dropdown:: Partially configurable model with no default .. code-block:: python # pip install langchain langchain-openai langchain-anthropic from langchain.chat_models import init_chat_model # We don't need to specify configurable=True if a model isn't specified. configurable_model = init_chat_model(temperature=0) configurable_model.invoke( "what's your name", config={"configurable": {"model": "gpt-4o"}} ) # GPT-4o response configurable_model.invoke( "what's your name", config={"configurable": {"model": "claude-3-5-sonnet-20240620"}} ) # claude-3.5 sonnet response .. dropdown:: Fully configurable model with a default .. code-block:: python # pip install langchain langchain-openai langchain-anthropic from langchain.chat_models import init_chat_model configurable_model_with_default = init_chat_model( "gpt-4o", model_provider="openai", configurable_fields="any", # this allows us to configure other params like temperature, max_tokens, etc at runtime. config_prefix="foo", temperature=0 ) configurable_model_with_default.invoke("what's your name") # GPT-4o response with temperature 0 configurable_model_with_default.invoke( "what's your name", config={ "configurable": { "foo_model": "claude-3-5-sonnet-20240620", "foo_model_provider": "anthropic", "foo_temperature": 0.6 } } ) # Claude-3.5 sonnet response with temperature 0.6 .. dropdown:: Bind tools to a configurable model You can call any ChatModel declarative methods on a configurable model in the same way that you would with a normal model. .. code-block:: python # pip install langchain langchain-openai langchain-anthropic from langchain.chat_models import init_chat_model from pydantic import BaseModel, Field class GetWeather(BaseModel): '''Get the current weather in a given location''' location: str = Field(..., description="The city and state, e.g. San Francisco, CA") class GetPopulation(BaseModel): '''Get the current population in a given location''' location: str = Field(..., description="The city and state, e.g. San Francisco, CA") configurable_model = init_chat_model( "gpt-4o", configurable_fields=("model", "model_provider"), temperature=0 ) configurable_model_with_tools = configurable_model.bind_tools([GetWeather, GetPopulation]) configurable_model_with_tools.invoke( "Which city is hotter today and which is bigger: LA or NY?" ) # GPT-4o response with tool calls configurable_model_with_tools.invoke( "Which city is hotter today and which is bigger: LA or NY?", config={"configurable": {"model": "claude-3-5-sonnet-20240620"}} ) # Claude-3.5 sonnet response with tools .. versionadded:: 0.2.7 .. versionchanged:: 0.2.8 Support for ``configurable_fields`` and ``config_prefix`` added. .. versionchanged:: 0.2.12 Support for ChatOllama via langchain-ollama package added (langchain_ollama.ChatOllama). Previously, the now-deprecated langchain-community version of Ollama was imported (langchain_community.chat_models.ChatOllama). Support for langchain_aws.ChatBedrockConverse added (model_provider="bedrock_converse"). .. versionchanged:: 0.3.5 Out of beta. r'r#zconfig_prefix=z has been set but no fields are configurable. Set `configurable_fields=(...)` to specify the model params that are configurable.r#r')default_configr%r$N)warningswarn_init_chat_model_helperrr&r.r,r+r+r-r"Us2[ )r#)r'r#r(r)c Ks|t||\}}|dkrrDrSrMr`rGrPr>rJrYr\r<r6rArVr^r9) model_namer)csvtfdddDrdSdr(dSdr6dSd rDd Sd rRd Sd r`dSdrndSdSdS)Nc3s|]}|VqdSr*) startswith).0prerlr+r- z0_attempt_infer_model_provider..)zgpt-3zgpt-4Zo1r6Zclauder9commandr>zaccounts/fireworksrGgeminirAzamazon.rYZmistralrP)anyrmrpr+rpr-_attempt_infer_model_providers      rvzTuple[str, str])r'r#r)cCs||sDd|vrD|ddtvrD|dd}d|ddd}|pNt|}|sdtd|d|dd}||fS)N:rz)Unable to infer model provider for model=z), please specify model_provider directly.-_)splitrirhrvrjreplacelowerr0r+r+r-res  rerbNone)pkgrcr)cCs<t|s8|dur|n |dd}td|d|ddS)NrzryzUnable to import z&. Please install with `pip install -U `)r find_specr|rg)rrcr+r+r-rfs  rf)sprefixr)cCs||r|t|d}|Sr*)rmlen)rrr+r+r-_remove_prefixs r) bind_toolswith_structured_outputcseZdZddddddddd d d d d ZdddddZdedddddZdddddZdfddddddZedddd Z dgd!dddd"d#d$Z dhd!dddd"d%d&Z did!dd'd(d"d)d*Z djd!dd'd+d"d,d-Z dkd.d/d0d1d2d'd3d4fd5d6Zdld.d/d0d1d2d'd3d4fd7d8Zdmd.d/d9d:d2dd;d4fdd4fd?d@ZdodAdd'd(d"dBdCZdpdDdd'd+d"dEdFZedqdGdGdddddddHdddId2dJdJdJdJdJdJddKdL dMdNZedrdGdddddddOdddPd2dJdJdJdJdJdJddQdL dRdNZdsdGdGdddddddHddd2d2dJdJdJdJdJdJddSdL dTdNZdtdddddddUdddVdJdJdJdJdJdJddWdX dYdZZd[dd\d]d^d_Zd`ddadbdcddZZS)ur.Nrur1r+r2r$r%queued_declarative_operationszOptional[dict]r/r&z!Sequence[Tuple[str, Tuple, Dict]]r~)r2r$r%rr)cCsJ|pi|_|dkr|nt||_|r6|ds6|dn||_t||_dS)Nrurz)_default_configlist_configurable_fieldsendswith_config_prefix_queued_declarative_operations)selfr2r$r%rr+r+r-__init__s  z_ConfigurableModel.__init__r)namer)csvtvr$ddddfdd }|SjrJ}rJt|rJt|Sd}jrb|d7}|d7}t|dS) Nrr.)argsr(r)csJtj}|||fttjtjtr:tjnjj|dS)Nr) rrappendr.dictr isinstancerr)rr(rrrr+r-queues z-_ConfigurableModel.__getattr__..queuez! is not a BaseChatModel attributez, and is not implemented on the default model.)_DECLARATIVE_METHODSr_modelhasattrgetattrAttributeError)rrrr'msgr+rr- __getattr__s  z_ConfigurableModel.__getattr__zOptional[RunnableConfig]r)configr)cCsLi|j||}tfi|}|jD]\}}}t|||i|}q(|Sr*)r _model_paramsr5rr)rrparamsr'rrr(r+r+r-r1s z_ConfigurableModel._modelrcsJt|}fdd|diD}jdkrFfdd|D}|S)Ncs*i|]"\}}|jrt|j|qSr+)rmrrrnkvrr+r- :s z4_ConfigurableModel._model_params.. configurablerucs i|]\}}|jvr||qSr+)rrrr+r-r@s)rgetitemsr)rr model_paramsr+rr-r8s   z _ConfigurableModel._model_params)rr(r)c stfi|p itt|}|dd|D}fdd|diD|d<tj}|r~|ddd|iftij t j trtj nj j |dS) z4Bind config to a Runnable, returning a new Runnable.cSsi|]\}}|dkr||qS)rr+rr+r+r-rMrrz2_ConfigurableModel.with_config..cs&i|]\}}t|jvr||qSr+)rrrrrr+r-rNsr with_configr+rr) rrrrrrrrr.rrrr)rrr(Zremaining_configrr+rr-rEs,      z_ConfigurableModel.with_configr!)r)cCs*ddlm}m}ttt||fttfS)z%Get the input type for this runnable.r)ChatPromptValueConcreteStringPromptValue)Zlangchain_core.prompt_valuesrrrr&r r)rrrr+r+r- InputTypees z_ConfigurableModel.InputTyper)inputrr(r)cKs||j|fd|i|SNr)rinvokerrrr(r+r+r-rvsz_ConfigurableModel.invokecs"||j|fd|i|IdHSr)rainvokerr+r+r-r~sz_ConfigurableModel.ainvokez Optional[Any]z Iterator[Any]cks&||j|fd|i|EdHdSr)rstreamrr+r+r-rsz_ConfigurableModel.streamzAsyncIterator[Any]cKs6||j|fd|i|2z3dHW}|Vq6dSr)rastreamrrrr(xr+r+r-rs(z_ConfigurableModel.astreamF)return_exceptionszList[LanguageModelInput]z5Optional[Union[RunnableConfig, List[RunnableConfig]]]boolz List[Any])inputsrrr(r)c st|pd}|dus&t|ts&t|dkrVt|tr8|d}||j|f||d|Stj|f||d|SdSNrxr)rr)rrrrrbatchsuperrrrrr( __class__r+r-rs$  z_ConfigurableModel.batchcs|pd}|dus&t|ts&t|dkr\t|tr8|d}||j|f||d|IdHStj|f||d|IdHSdSr)rrrrrabatchrrrr+r-rs$   z_ConfigurableModel.abatchzSequence[LanguageModelInput]z9Optional[Union[RunnableConfig, Sequence[RunnableConfig]]]z+Iterator[Tuple[int, Union[Any, Exception]]]c+s|pd}|dus&t|ts&t|dkrdt|tr8|d}|tt|j|f||d|EdHn tj|f||d|EdHdSr) rrrrrrrbatch_as_completedrrrr+r-rs$ z%_ConfigurableModel.batch_as_completedzAsyncIterator[Tuple[int, Any]]c s|pd}|dus&t|ts&t|dkrtt|tr8|d}|tt|j|f||d|2z3dHW}|Vq\6n0tj|f||d|2z3dHW}|Vq6dSr) rrrrrrrabatch_as_completedr)rrrrr(rrr+r-rs,  z&_ConfigurableModel.abatch_as_completedzIterator[LanguageModelInput]cks,||j|fd|i|D] }|VqdSr)r transformrr+r+r-rs z_ConfigurableModel.transformz!AsyncIterator[LanguageModelInput]cKs6||j|fd|i|2z3dHW}|Vq6dSr)r atransformrr+r+r-rs(z_ConfigurableModel.atransformT)diffwith_streamed_output_list include_names include_types include_tags exclude_names exclude_types exclude_tagsz Literal[True]zOptional[Sequence[str]]zAsyncIterator[RunLogPatch]) rrrrrrrrrrr(r)c KsdSr*r+ rrrrrrrrrrrr(r+r+r- astream_log sz_ConfigurableModel.astream_log)rrrrrrrzLiteral[False]zAsyncIterator[RunLog]c KsdSr*r+rr+r+r-rsz8Union[AsyncIterator[RunLogPatch], AsyncIterator[RunLog]]c KsF||j|f||||||| | |d | 2z3dHW} | Vq,6dS)N) rrrrrrrrr)rr) rrrrrrrrrrrr(rr+r+r-r+s    )rrrrrrzLiteral['v1', 'v2']zAsyncIterator[StreamEvent]) rrversionrrrrrrr(r)c KsD||j|f|||||| ||d| 2z3dHW} | Vq*6dS)N)rrrrrrrr)rastream_events) rrrrrrrrrrr(rr+r+r-rIs   z!_ConfigurableModel.astream_eventszDSequence[Union[Dict[str, Any], Type[BaseModel], Callable, BaseTool]]z)Runnable[LanguageModelInput, BaseMessage])toolsr(r)cKs|d|fi|S)Nrr)rrr(r+r+r-rfsz_ConfigurableModel.bind_toolszUnion[Dict, Type[BaseModel]]z4Runnable[LanguageModelInput, Union[Dict, BaseModel]])schemar(r)cKs|d|fi|S)Nrr)rrr(r+r+r-rnsz)_ConfigurableModel.with_structured_output)N)N)N)N)N)N)N)N)N)N)N)N)N)N)N)N)__name__ __module__ __qualname__rrrrrpropertyrrrrrrrrrrrrrrrr __classcell__r+r+rr-r.s       **(!&)N)N)N)7 __future__rr3 importlibrtypingrrrrrr r r r r rrrrZlangchain_core.language_modelsrrrZ*langchain_core.language_models.chat_modelsrrZlangchain_core.messagesrrZlangchain_core.runnablesrrrZlangchain_core.runnables.schemarZlangchain_core.toolsrZlangchain_core.tracersrrZpydanticr Ztyping_extensionsr!__all__r"r5rirvrerfrrr.r+r+r+r-s`  @       vg