3fiddlmZddlZddlmZmZmZmZddlm Z ddl m Z m Z m Z mZmZddlmZmZmZddlmZmZddlmZmZdd lmZmZmZdd lmZdd l m!Z!dd l"m#Z#m$Z$dd l%m&Z&ddl'm(Z(gdZ)edddd d dZ*e d!dddd d"dZ*e d!dddd d#dZ* d!dddd d$dZ*dd d%dZ+hdZ,d&dZ-d'dZ.ddd(dZ/dZ0Gddeee fZ1y))) annotationsN) AsyncIteratorCallableIteratorSequence)util)AnyLiteral TypeAliascastoverload) BaseChatModelLanguageModelInputSimpleChatModel)agenerate_from_streamgenerate_from_stream) AIMessage AnyMessage)RunnableRunnableConfig ensure_config) StreamEvent)BaseTool)RunLog RunLogPatch) BaseModel)override)rrrrinit_chat_model)model_providerconfigurable_fields config_prefixc yNmodelrr r!kwargss `/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_classic/chat_models/base.pyrr#s_ConfigurableModelc yr#r$r%s r(rr.r).c yr#r$r%s r(rr9r,r)c |s|sd}|xsd}|r|stjd|dd|sttd|fd|i|S|r||d <|r||d<t ||| S) u1Initialize a chat model from any supported provider using a unified interface. **Two main use cases:** 1. **Fixed model** – specify the model upfront and get back a ready-to-use chat model. 2. **Configurable model** – choose to specify parameters (including model name) at runtime via `config`. Makes it easy to switch between models/providers without changing your code !!! note Requires the integration package for the chosen model provider to be installed. See the `model_provider` parameter below for specific package names (e.g., `pip install langchain-openai`). Refer to the [provider integration's API reference](https://docs.langchain.com/oss/python/integrations/providers) for supported model parameters to use as `**kwargs`. Args: model: The name or ID of the model, e.g. `'o3-mini'`, `'claude-sonnet-4-5-20250929'`. You can also specify model and model provider in a single argument using `'{model_provider}:{model}'` format, e.g. `'openai:o1'`. Will attempt to infer `model_provider` from model if not specified. The following providers will be inferred based on these model prefixes: - `gpt-...` | `o1...` | `o3...` -> `openai` - `claude...` -> `anthropic` - `amazon...` -> `bedrock` - `gemini...` -> `google_vertexai` - `command...` -> `cohere` - `accounts/fireworks...` -> `fireworks` - `mistral...` -> `mistralai` - `deepseek...` -> `deepseek` - `grok...` -> `xai` - `sonar...` -> `perplexity` model_provider: The model provider if not specified as part of the model arg (see above). Supported `model_provider` values and the corresponding integration package are: - `openai` -> [`langchain-openai`](https://docs.langchain.com/oss/python/integrations/providers/openai) - `anthropic` -> [`langchain-anthropic`](https://docs.langchain.com/oss/python/integrations/providers/anthropic) - `azure_openai` -> [`langchain-openai`](https://docs.langchain.com/oss/python/integrations/providers/openai) - `azure_ai` -> [`langchain-azure-ai`](https://docs.langchain.com/oss/python/integrations/providers/microsoft) - `google_vertexai` -> [`langchain-google-vertexai`](https://docs.langchain.com/oss/python/integrations/providers/google) - `google_genai` -> [`langchain-google-genai`](https://docs.langchain.com/oss/python/integrations/providers/google) - `bedrock` -> [`langchain-aws`](https://docs.langchain.com/oss/python/integrations/providers/aws) - `bedrock_converse` -> [`langchain-aws`](https://docs.langchain.com/oss/python/integrations/providers/aws) - `cohere` -> [`langchain-cohere`](https://docs.langchain.com/oss/python/integrations/providers/cohere) - `fireworks` -> [`langchain-fireworks`](https://docs.langchain.com/oss/python/integrations/providers/fireworks) - `together` -> [`langchain-together`](https://docs.langchain.com/oss/python/integrations/providers/together) - `mistralai` -> [`langchain-mistralai`](https://docs.langchain.com/oss/python/integrations/providers/mistralai) - `huggingface` -> [`langchain-huggingface`](https://docs.langchain.com/oss/python/integrations/providers/huggingface) - `groq` -> [`langchain-groq`](https://docs.langchain.com/oss/python/integrations/providers/groq) - `ollama` -> [`langchain-ollama`](https://docs.langchain.com/oss/python/integrations/providers/ollama) - `google_anthropic_vertex` -> [`langchain-google-vertexai`](https://docs.langchain.com/oss/python/integrations/providers/google) - `deepseek` -> [`langchain-deepseek`](https://docs.langchain.com/oss/python/integrations/providers/deepseek) - `ibm` -> [`langchain-ibm`](https://docs.langchain.com/oss/python/integrations/providers/ibm) - `nvidia` -> [`langchain-nvidia-ai-endpoints`](https://docs.langchain.com/oss/python/integrations/providers/nvidia) - `xai` -> [`langchain-xai`](https://docs.langchain.com/oss/python/integrations/providers/xai) - `perplexity` -> [`langchain-perplexity`](https://docs.langchain.com/oss/python/integrations/providers/perplexity) configurable_fields: Which model parameters are configurable at runtime: - `None`: No configurable fields (i.e., a fixed model). - `'any'`: All fields are configurable. **See security note below.** - `list[str] | Tuple[str, ...]`: Specified fields are configurable. Fields are assumed to have `config_prefix` stripped if a `config_prefix` is specified. If `model` is specified, then defaults to `None`. If `model` is not specified, then defaults to `("model", "model_provider")`. !!! warning "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: Optional prefix for configuration keys. Useful when you have multiple configurable models in the same application. If `'config_prefix'` is a non-empty string then `model` will be configurable at runtime via the `config["configurable"]["{config_prefix}_{param}"]` keys. See examples below. If `'config_prefix'` is an empty string then model will be configurable via `config["configurable"]["{param}"]`. **kwargs: Additional model-specific keyword args to pass to the underlying chat model's `__init__` method. Common parameters include: - `temperature`: Model temperature for controlling randomness. - `max_tokens`: Maximum number of output tokens. - `timeout`: Maximum time (in seconds) to wait for a response. - `max_retries`: Maximum number of retry attempts for failed requests. - `base_url`: Custom API endpoint URL. - `rate_limiter`: A [`BaseRateLimiter`][langchain_core.rate_limiters.BaseRateLimiter] instance to control request rate. Refer to the specific model provider's [integration reference](https://reference.langchain.com/python/integrations/) for all available parameters. Returns: A [`BaseChatModel`][langchain_core.language_models.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. ???+ example "Initialize a non-configurable model" ```python # pip install langchain langchain-openai langchain-anthropic langchain-google-vertexai from langchain_classic.chat_models import init_chat_model o3_mini = init_chat_model("openai:o3-mini", temperature=0) claude_sonnet = init_chat_model("anthropic:claude-sonnet-4-5-20250929", temperature=0) gemini_2-5_flash = init_chat_model( "google_vertexai:gemini-2.5-flash", temperature=0 ) o3_mini.invoke("what's your name") claude_sonnet.invoke("what's your name") gemini_2-5_flash.invoke("what's your name") ``` ??? example "Partially configurable model with no default" ```python # pip install langchain langchain-openai langchain-anthropic from langchain_classic.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"}} ) # Use GPT-4o to generate the response configurable_model.invoke( "what's your name", config={"configurable": {"model": "claude-sonnet-4-5-20250929"}}, ) ``` ??? example "Fully configurable model with a default" ```python # pip install langchain langchain-openai langchain-anthropic from langchain_classic.chat_models import init_chat_model configurable_model_with_default = init_chat_model( "openai:gpt-4o", 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 (as set in default) configurable_model_with_default.invoke( "what's your name", config={ "configurable": { "foo_model": "anthropic:claude-sonnet-4-5-20250929", "foo_temperature": 0.6, } }, ) # Override default to use Sonnet 4.5 with temperature 0.6 to generate response ``` ??? example "Bind tools to a configurable model" You can call any chat model declarative methods on a configurable model in the same way that you would with a normal model: ```python # pip install langchain langchain-openai langchain-anthropic from langchain_classic.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?" ) # Use GPT-4o configurable_model_with_tools.invoke( "Which city is hotter today and which is bigger: LA or NY?", config={"configurable": {"model": "claude-sonnet-4-5-20250929"}}, ) # Use Sonnet 4.5 ``` !!! warning "Behavior changed in `langchain` 0.2.8" Support for `configurable_fields` and `config_prefix` added. !!! warning "Behavior changed in `langchain` 0.2.12" Support for Ollama 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 AWS Bedrock models via the Converse API added (`model_provider="bedrock_converse"`). !!! warning "Behavior changed in `langchain` 0.3.5" Out of beta. !!! warning "Behavior changed in `langchain` 0.3.19" Support for Deepseek, IBM, Nvidia, and xAI models added. )r&rzconfig_prefix=z has been set but no fields are configurable. Set `configurable_fields=(...)` to specify the model params that are configurable.) stacklevelstrrr&)default_configr!r )warningswarn_init_chat_model_helperr r*r%s r(rrGsb ,9!'RM0 }    &   )    w#1 #/ r))rc t||\}}|dk(rtdddlm}|dId|i|S|dk(rtdddlm}|dId|i|S|d k(rtddd lm}|dId|i|S|d k(rtd dd lm}|dId|i|S|dk(rtdddl m }|dId|i|S|dk(rtdddl m }|dId|i|S|dk(rtdddl m} | dId|i|S|dk(rtdddlm} | dId|i|S|dk(r tdddlm}  dId|i|S|dk(rtddd lm} | dId|i|S|d!k(rtd"dd#lm} | dId|i|S|d$k(r%td%dd&lm}|j6dId'|i|S|d(k(rtd)dd*lm}|dId|i|S|d+k(rtd,dd-lm}|dId'|i|S|d.k(rtd,dd/lm }|dId|i|S|d0k(rtddd1l!m"}|dId|i|S|d2k(rtd3d45dd6l#m$}|dId|i|S|d7k(rtd8dd9l%m&}|dId|i|S|d:k(rtd;dddd?l)m*}|dId|i|S|d@k(rtdAddBl+m,}|dId|i|S|dCk(rtdDddEl-m.}|dId|i|SdFj_t`}dG|dH|}tc|#t&$r1 tdddlm} n#t&$rtdYnwxYwYwxYw)JNopenailangchain_openair) ChatOpenAIr& anthropiclangchain_anthropic) ChatAnthropic azure_openai)AzureChatOpenAIazure_ailangchain_azure_ai)AzureAIChatCompletionsModelcoherelangchain_cohere) ChatCoheregoogle_vertexailangchain_google_vertexai) ChatVertexAI google_genailangchain_google_genai)ChatGoogleGenerativeAI fireworkslangchain_fireworks) ChatFireworksollamalangchain_ollama) ChatOllamalangchain_communitytogetherlangchain_together) ChatTogether mistralailangchain_mistralai) ChatMistralAI huggingfacelangchain_huggingface)ChatHuggingFacemodel_idgroqlangchain_groq)ChatGroqbedrock langchain_aws) ChatBedrockbedrock_converse)ChatBedrockConversegoogle_anthropic_vertex)ChatAnthropicVertexdeepseeklangchain_deepseekzlangchain-deepseek pkg_kebab) ChatDeepSeeknvidialangchain_nvidia_ai_endpoints) ChatNVIDIAibm langchain_ibm) ChatWatsonxxai langchain_xai)ChatXAI perplexitylangchain_perplexity)ChatPerplexityupstagelangchain_upstage) ChatUpstage, zUnsupported model_provider=z". Supported model providers are: r$)2 _parse_model _check_pkgr9r:r<r=r?langchain_azure_ai.chat_modelsrBrDrErGrHrJrKrMrNrPrQ ImportErrorlangchain_community.chat_modelsrTrUrWrXrZr[ from_model_idr^r_rarbrd&langchain_google_vertexai.model_gardenrfrhrkrmrnrprqrsrtrvrwryrzjoin_SUPPORTED_PROVIDERS ValueError)r&rr'r:r=r?rBrErHrKrNrQrUrXr[r_rbrdrfrkrnrqrtrwrz supportedmsgs r(r6r6ts )?E>!%&/0000$()5353F33'%&45U5f55#'(N*AA&AA!%&/0000**./:2%2622'+,A%L?>rorrr]rCrOr8r`rxr@rgrSr;rLrVrurYr>rIrFrcrec|jtfddDryjdryjdry|jdry jd ry |jd sjd ryjdryjdryjdryjdryjdryy)zAttempt to infer model provider from model name. Args: model_name: The name of the model to infer provider for. Returns: The inferred provider name, or `None` if no provider could be inferred. c3@K|]}j|ywr#) startswith).0pre model_lowers r( z0_attempt_infer_model_provider.."s$   s# s)zgpt-o1o3chatgptz text-davincir8clauder;commandrCzaccounts/fireworksrLgeminirFzamazon.)z anthropic.zmeta.r`)mistralmixtralrVrggrokrrsonarrusolarrxN)loweranyr) model_namers @r(_attempt_infer_model_providerrs""$K    h'i(12h' Y';+A+A,45j)f%g&g& r)cB|s7d|vr3|jdd\}}|tvr|}|}nt|}|r|}|}|xs t|}|s2djt t}d|d|d}t ||j ddj}||fS) z?Parse model name and provider, inferring provider if necessary.:r{z)Unable to infer model provider for model=zB. Please specify 'model_provider' directly. Supported providers: ze For help with specific providers, see: https://docs.langchain.com/oss/python/integrations/providers-_)splitrrrsortedrreplacer)r&rprefixsuffixinferredsupported_listrs r(r|r|[s cUlS!, ) )#NE4V#?@8%:$$2#34K L o$++C5;;=N .  r)rictj|s*||n|jdd}d|d|d}t|y)NrrzUnable to import z&. Please install with `pip install -U `)r find_specrr)pkgrjrs r(r}r}ysP >># !*!6ICKKS.queues~04771-.44dD&5IJ)#'(<(<#=!$";";TB)-T-F-F(G22"&"5"52O r)z! is not a BaseChatModel attributez, and is not implemented on the default model.)rr r'r returnr*)_DECLARATIVE_METHODSr_modelhasattrgetattrAttributeError)rrrr&rs`` r( __getattr__z_ConfigurableModel.__getattr__s} ' ' L   dkkm%;U%;PTAU5$' '78    A AC s S!!r)ci|j|j|}tdi|}|jD]\}}}t |||i|}|S)Nr$)r _model_paramsr6rr)rconfigparamsr&rrr's r(rz_ConfigurableModel._modelshGD((GD,>,>v,FG'1&1"&"E"E : D$(GE4($9&9E : r)ct|}|jdijDcic]<\}}|j|jr|j |j|>}}}|j dk7r2|jDcic]\}}||j vs||}}}|Scc}}wcc}}w)N configurabler)rgetitemsrr removeprefixr)rrkv model_paramss r(rz _ConfigurableModel._model_paramssv& >26<<> 1||D//0 NN4.. / 2   $ $ -!-!3!3!5Ad>W>W9W1L sAB6B<,B<c tdi|xsitd|}|j|}|jDcic]\}}|dk7s ||}}}|j dijDcic]%\}}|j |j |vr||'c}}|d<t|j}|r|jddd|ifti|j|t|jtrt|jn |j|j |Scc}}wcc}}w)z8Bind config to a `Runnable`, returning a new `Runnable`.rr with_configr$rr)rr rrrrrrrrr*rrr)rrr'rrrremaining_configrs r(rz_ConfigurableModel.with_configsH  S626<<>, 1~~d112,F qD, ( )-T-P-P(Q%  ) 0 0!/0 "Cd22ClC$33T:!%T%>%> ?**--*G   T, s D7D79*D=cFddlm}m}t|z|ztt zS)z'Get the input type for this `Runnable`.r)ChatPromptValueConcreteStringPromptValue)langchain_core.prompt_valuesrrr2rr)rrrs r( InputTypez_ConfigurableModel.InputTypes% &&)@@4 CSSSr)c J|j|j|fd|i|SNr)rinvokerinputrr's r(rz_ConfigurableModel.invokes**t{{6"))%II&IIr)cfK|j|j|fd|i|d{S7wr)rainvokers r(rz_ConfigurableModel.ainvokes41T[[(00PvPPPPPs (1/1c+hK|j|j|fd|i|Ed{y7wr)rstreamrs r(rz_ConfigurableModel.streams1.4;;v&--eMFMfMMM (202c xK|j|j|fd|i|23d{}|7 6ywr)rastreamrrrr'xs r(rz_ConfigurableModel.astreamsE3t{{6*225RR6R  !G R%:868:8:F)return_exceptionsc |xsd}|t|tst|dkr:t|tr|d}|j |j |f||d|St ||f||d|SNrrrr)rrlenrrbatchsuperrinputsrrr' __class__s r(rz_ConfigurableModel.batch"s4 >Z5V9I&$',4;;v&,,"3  w}  /    r)cK|xsd}|t|tst|dkrBt|tr|d}|j |j |f||d|d{St ||f||d|d{S77wr)rrrrrabatchrrs r(rz_ConfigurableModel.abatch>s4 >Z5V9I&$'3V,33"3  W^  /      s$A$B 'B(B B B  B c+2K|xsd}|t|tst|dkrMt|tr|d}|j t d|j |f||d|Ed{yt||f||d|Ed{y7!7wNrrrr)rrrrrr batch_as_completedrrs r(rz%_ConfigurableModel.batch_as_completedZs4 >Z5V9I&$'Ut{{4(8&#ABUU"3   w1"3     s$A.B1B2B BBBc RK|xsd}|t|tst|dkrSt|tr|d}|j t d|j |f||d|23d{}|t||f||d|23d{}|7,6y76ywr)rrrrrr abatch_as_completedr)rrrrr'rrs r(rz&_ConfigurableModel.abatch_as_completedws4 >Z5V9I&$'"4;;%v.!!"3     a!76"3   a %  sNA+B'.B!2B3B!6B'B%B#B%B'B!!B'#B%%B'c+hK|j|j|fd|i|Ed{y7wr)r transformrs r(rz_ConfigurableModel.transforms114;;v&00PvPPPPrc xK|j|j|fd|i|23d{}|7 6ywr)r atransformrs r(rz_ConfigurableModel.atransformsE6t{{6*55eUFUfU  !G UrT)diffwith_streamed_output_list include_names include_types include_tags exclude_names exclude_types exclude_tagsc yr#r$ rrrrrrrrr r r r's r( astream_logz_ConfigurableModel.astream_logs&)r))rrrrr r r c yr#r$r s r(rz_ConfigurableModel.astream_logs!$r)c K|j|j|f||||||| | |d | 23d{} | 7 6yw)N) rrrrrrr r r )rr) rrrrrrrrr r r r'rs r(rz_ConfigurableModel.astream_logsl 7t{{6*66   &?''%%''     !G   s#-AA>AAAAv2)versionrrrr r r c K|j|j|f|||||| ||d| 23d{} | 7 6yw)N)rrrrrr r r )rastream_events) rrrrrrrr r r r'rs r(rz!_ConfigurableModel.astream_eventssi:t{{6*99   ''%%''     !G   s,A?=?A?Ac 2|jd|fi|S)Nrr)rtoolsr's r(rz_ConfigurableModel.bind_tools s! .t -e>v>>r)c 2|jd|fi|S)Nrr)rschemar's r(rz)_ConfigurableModel.with_structured_outputs" :t 89&KFKKr)) r3z dict | Noner ,Literal['any'] | list[str] | tuple[str, ...]r!r2rz!Sequence[tuple[str, tuple, dict]]rNone)rr2rr r#)rRunnableConfig | Nonerr)rrrr)rrr'r rr*)rr )rrrrr'r rr )rrrrr' Any | Noner Iterator[Any])rrrrr'rrAsyncIterator[Any]) rzlist[LanguageModelInput]rz,RunnableConfig | list[RunnableConfig] | Nonerboolr'rrz list[Any]) rSequence[LanguageModelInput]r0RunnableConfig | Sequence[RunnableConfig] | Nonerr r'r rz%Iterator[tuple[int, Any | Exception]]) rr!rr"rr r'r rzAsyncIterator[tuple[int, Any]])rzIterator[LanguageModelInput]rrr'rrr)rz!AsyncIterator[LanguageModelInput]rrr'rrr)rr rrrz Literal[True]rr rSequence[str] | Nonerr#rr#r r#r r#r r#r'r rzAsyncIterator[RunLogPatch])rr rrrzLiteral[False]rr rr#rr#rr#r r#r r#r r#r'r rzAsyncIterator[RunLog])rr rrrr rr rr#rr#rr#r r#r r#r r#r'r rz2AsyncIterator[RunLogPatch] | AsyncIterator[RunLog])rr rrrzLiteral['v1', 'v2']rr#rr#rr#r r#r r#r r#r'r rzAsyncIterator[StreamEvent])rz@Sequence[dict[str, Any] | type[BaseModel] | Callable | BaseTool]r'r rz'Runnable[LanguageModelInput, AIMessage])rzdict | type[BaseModel]r'r rz.Runnable[LanguageModelInput, dict | BaseModel])__name__ __module__ __qualname__rrrrrpropertyrrrrrrrrrrrrr rrrr __classcell__)rs@r(r*r*s:'+LQKM  $ J    (I    ."< )- %     @  T T)-J!J&J J JJ)-Q!Q&Q Q QQ)-N!N&N N  NN)-!&   @D #(  ( =       >@D #(  ( =       >DH #( ,A     /@DH #( ,A     (B)-Q+Q&Q Q  QQ)-0&   )-) #*..2.2-1.2.2-1))&)  ) $( ),),)+),),)+)) $)) )-$ +/.2.2-1.2.2-1$$&$  $ $( $,$,$+$,$,$+$$ $$ )- *..2.2-1.2.2-1&   $( ,,+,,+ <<)- (,.2.2-1.2.2-1& %  , ,+,,+ $:?O?? 1 ?L&LL 8 Lr)) r&r2r str | Noner rr!r)r'r rrr#) r&rrr)r rr!r)r'r rr*) r&r)rr)r rr!r)r'r rr*) r&r)rr)r z3Literal['any'] | list[str] | tuple[str, ...] | Noner!r)r'r rz"BaseChatModel | _ConfigurableModel)r&r2rr)r'r rr)rr2rr))r&r2rr)rztuple[str, str])rr2rjr)rr)2 __future__rr4collections.abcrrrr importlibrtypingr r r r r langchain_core.language_modelsrrr*langchain_core.language_models.chat_modelsrrlangchain_core.messagesrrlangchain_core.runnablesrrrlangchain_core.runnables.schemarlangchain_core.toolsrlangchain_core.tracersrrpydanticrtyping_extensionsr__all__rr6rrr|r}rr*r$r)r(r8s<"GG:: :LL7)6&  "& $ $         "& $ $         "&HK $  F      j"&OS $ j jjM j  j  j(j` "&F FF F  FR2BJ!<59@RL"4c"9:RLr)