@'hb8dZddlmZddlZddlZddlmZddlmZm Z m Z m Z m Z m Z mZmZmZmZmZmZmZmZmZddlmZddlmZmZddlmZdd lmZm Z m!Z!m"Z"dd l#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)m*Z*m+Z+m,Z,m-Z-m.Z.m/Z/m0Z0m1Z1m2Z2m3Z3dd l4m5Z5m6Z6dd l7m8Z8dd l9m:Z:m;Z;mm?Z?m@Z@mAZAddlBmCZCmDZDmEZEddlFmGZGddlHmIZImJZJmKZKddlLmMZMmNZNddlOmPZPddlQmRZRmSZSmTZTmUZUmVZVddlWmXZXddlYmZZZGddeZ[d!dZ\GddeZ]d"dZ^ d#dZ_d$dZ`d%dZa d&d Zby)'zGroq Chat wrapper.) annotationsN) itemgetter)Any AsyncIteratorCallableDictIteratorListLiteralMappingOptionalSequenceTupleType TypedDictUnioncast) deprecated)AsyncCallbackManagerForLLMRunCallbackManagerForLLMRun)LanguageModelInput) BaseChatModelLangSmithParamsagenerate_from_streamgenerate_from_stream) AIMessageAIMessageChunk BaseMessageBaseMessageChunk ChatMessageChatMessageChunkFunctionMessageFunctionMessageChunk HumanMessageHumanMessageChunkInvalidToolCall SystemMessageSystemMessageChunkToolCall ToolMessageToolMessageChunk)JsonOutputParserPydanticOutputParser)OutputParserLike)JsonOutputKeyToolsParserPydanticToolsParsermake_invalid_tool_callparse_tool_call)ChatGenerationChatGenerationChunk ChatResult)Runnable RunnableMapRunnablePassthrough)BaseTool)from_envget_pydantic_field_namessecret_from_env)convert_to_openai_functionconvert_to_openai_tool)is_basemodel_subclass) BaseModel ConfigDictField SecretStrmodel_validator)Self) __version__ceZdZUdZeddZded<eddZded<ed Zd ed < d Z d ed< eddZ ded< ee Z ded< ede ddZded< ededdZded< eed dZded!<edd"Zd#ed$< d%Zd&ed'< d(Zd)ed*< d+Zd&ed,< dZd-ed.< dZd/ed0<dZd1ed2<dZd3ed4< dZd3ed5< ed6Zed78edTd9Zed:8dUd;Z e!dVd<Z"edWd=Z#e!dXd>Z$ dY dZd?Z%dd@ d[fdAZ& d\ d]dBZ' d\ d^dCZ( d\ d_dDZ) d\ d`dEZ*e!dadFZ+dbdGZ, dcdHZ-dddIZ.e/dJdKdLM dY defdN Z0ddO dffdPZ1 dYdQd(dR dgdSZ2xZ3S)hChatGroqu`Groq` Chat large language models API. To use, you should have the environment variable ``GROQ_API_KEY`` set with your API key. Any parameters that are valid to be passed to the groq.create call can be passed in, even if not explicitly saved on this class. Setup: Install ``langchain-groq`` and set environment variable ``GROQ_API_KEY``. .. code-block:: bash pip install -U langchain-groq export GROQ_API_KEY="your-api-key" Key init args — completion params: model: str Name of Groq model to use. E.g. "llama-3.1-8b-instant". temperature: float Sampling temperature. Ranges from 0.0 to 1.0. max_tokens: Optional[int] Max number of tokens to generate. model_kwargs: Dict[str, Any] Holds any model parameters valid for create call not explicitly specified. Key init args — client params: timeout: Union[float, Tuple[float, float], Any, None] Timeout for requests. max_retries: int Max number of retries. api_key: Optional[str] Groq API key. If not passed in will be read from env var GROQ_API_KEY. base_url: Optional[str] Base URL path for API requests, leave blank if not using a proxy or service emulator. custom_get_token_ids: Optional[Callable[[str], List[int]]] Optional encoder to use for counting tokens. See full list of supported init args and their descriptions in the params section. Instantiate: .. code-block:: python from langchain_groq import ChatGroq llm = ChatGroq( model="llama-3.1-8b-instant", temperature=0.0, max_retries=2, # other params... ) Invoke: .. code-block:: python messages = [ ("system", "You are a helpful translator. Translate the user sentence to French."), ("human", "I love programming."), ] llm.invoke(messages) .. code-block:: python AIMessage(content='The English sentence "I love programming" can be translated to French as "J'aime programmer". The word "programming" is translated as "programmer" in French.', response_metadata={'token_usage': {'completion_tokens': 38, 'prompt_tokens': 28, 'total_tokens': 66, 'completion_time': 0.057975474, 'prompt_time': 0.005366091, 'queue_time': None, 'total_time': 0.063341565}, 'model_name': 'llama-3.1-8b-instant', 'system_fingerprint': 'fp_c5f20b5bb1', 'finish_reason': 'stop', 'logprobs': None}, id='run-ecc71d70-e10c-4b69-8b8c-b8027d95d4b8-0') Stream: .. code-block:: python for chunk in llm.stream(messages): print(chunk.text(), end="") .. code-block:: python content='' id='run-4e9f926b-73f5-483b-8ef5-09533d925853' content='The' id='run-4e9f926b-73f5-483b-8ef5-09533d925853' content=' English' id='run-4e9f926b-73f5-483b-8ef5-09533d925853' content=' sentence' id='run-4e9f926b-73f5-483b-8ef5-09533d925853' ... content=' program' id='run-4e9f926b-73f5-483b-8ef5-09533d925853' content='".' id='run-4e9f926b-73f5-483b-8ef5-09533d925853' content='' response_metadata={'finish_reason': 'stop'} id='run-4e9f926b-73f5-483b-8ef5-09533d925853 .. code-block:: python stream = llm.stream(messages) full = next(stream) for chunk in stream: full += chunk full .. code-block:: python AIMessageChunk(content='The English sentence "I love programming" can be translated to French as "J'aime programmer". Here's the breakdown of the sentence: * "J'aime" is the French equivalent of "I love" * "programmer" is the French infinitive for "to program" So, the literal translation is "I love to program". However, in English we often omit the "to" when talking about activities we love, and the same applies to French. Therefore, "J'aime programmer" is the correct and natural way to express "I love programming" in French.', response_metadata={'finish_reason': 'stop'}, id='run-a3c35ac4-0750-4d08-ac55-bfc63805de76') Async: .. code-block:: python await llm.ainvoke(messages) .. code-block:: python AIMessage(content='The English sentence "I love programming" can be translated to French as "J'aime programmer". The word "programming" is translated as "programmer" in French. I hope this helps! Let me know if you have any other questions.', response_metadata={'token_usage': {'completion_tokens': 53, 'prompt_tokens': 28, 'total_tokens': 81, 'completion_time': 0.083623752, 'prompt_time': 0.007365126, 'queue_time': None, 'total_time': 0.090988878}, 'model_name': 'llama-3.1-8b-instant', 'system_fingerprint': 'fp_c5f20b5bb1', 'finish_reason': 'stop', 'logprobs': None}, id='run-897f3391-1bea-42e2-82e0-686e2367bcf8-0') Tool calling: .. code-block:: python 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") model_with_tools = llm.bind_tools([GetWeather, GetPopulation]) ai_msg = model_with_tools.invoke("What is the population of NY?") ai_msg.tool_calls .. code-block:: python [{'name': 'GetPopulation', 'args': {'location': 'NY'}, 'id': 'call_bb8d'}] See ``ChatGroq.bind_tools()`` method for more. Structured output: .. code-block:: python from typing import Optional from pydantic import BaseModel, Field class Joke(BaseModel): '''Joke to tell user.''' setup: str = Field(description="The setup of the joke") punchline: str = Field(description="The punchline to the joke") rating: Optional[int] = Field(description="How funny the joke is, from 1 to 10") structured_model = llm.with_structured_output(Joke) structured_model.invoke("Tell me a joke about cats") .. code-block:: python Joke(setup="Why don't cats play poker in the jungle?", punchline='Too many cheetahs!', rating=None) See ``ChatGroq.with_structured_output()`` for more. Response metadata .. code-block:: python ai_msg = llm.invoke(messages) ai_msg.response_metadata .. code-block:: python {'token_usage': {'completion_tokens': 70, 'prompt_tokens': 28, 'total_tokens': 98, 'completion_time': 0.111956391, 'prompt_time': 0.007518279, 'queue_time': None, 'total_time': 0.11947467}, 'model_name': 'llama-3.1-8b-instant', 'system_fingerprint': 'fp_c5f20b5bb1', 'finish_reason': 'stop', 'logprobs': None} NT)defaultexcluderclient async_clientmodel)aliasstr model_namegffffff?float temperaturestop_sequences)rIrNzOptional[Union[List[str], str]]stop)default_factoryDict[str, Any] model_kwargsapi_key GROQ_API_KEY)rI)rNrUzOptional[SecretStr] groq_api_keybase_url GROQ_API_BASEz Optional[str] groq_api_base GROQ_PROXY groq_proxytimeoutz,Union[float, Tuple[float, float], Any, None]request_timeoutint max_retriesFbool streamingnz Optional[int] max_tokenszUnion[Mapping[str, str], None]default_headersz!Union[Mapping[str, object], None] default_queryzUnion[Any, None] http_clienthttp_async_client)populate_by_namebefore)modec `t|}|jdi}t|D]M}||vrtd|d||vst j d|d|d|d|j |||<O|j|j}|rtd|d ||d<|S) z>Build extra kwargs from additional params that were passed in.rWzFound z supplied twice.z WARNING! z/ is not default parameter. zJ was transferred to model_kwargs. Please confirm that z is what you intended.z Parameters za should be specified explicitly. Instead they were passed in as part of `model_kwargs` parameter.) r;getlist ValueErrorwarningswarnpop intersectionkeys)clsvaluesall_required_field_namesextra field_nameinvalid_model_kwargss a/home/kushmeetdev/Regenta/Chatbot/venv/lib/python3.12/site-packages/langchain_groq/chat_models.py build_extrazChatGroq.build_extrabs$2.v, ;JU" 6*5E!FGG!99 !*.L!))3 4JN %+JJz$:j! ; 8DDUZZ\R 234ST  "'~ afterc|jdkr td|jdkDr|jr td|jdk(rd|_ddtit |j xsiz}|jr|jjnd|j|j|j||jd } ddl }d |ji}|js-|j d i||j"j$|_|j&s;d |j(i}|j*d i||j"j$|_|S#t,$r t-d wxYw) z?Validate that api key and python package exists in environment.rgzn must be at least 1.zn must be 1 when streaming.rg:0yE>z User-Agentz langchain/N)rXr[r`rdrjrkrlzPCould not import groq python package. Please install it with `pip install groq`.)rhrtrfrRrFdictrjrZget_secret_valuer]rardrkgroqrlrKGroqchat completionsrLrm AsyncGroq ImportError)selfrj client_paramsr sync_specificasync_specifics rvalidate_environmentzChatGroq.validate_environment}s 66A:45 5 66A:$..:; ;   q #D ':k])CDt  &BH   9=8I8I!!224t**++++.!// )   -:D+,0GG G!!rc |jr!|j|f||d|}t|S|j||\}}i||}|jj dd|i|}|j |SN)rTrmessagesr)rf_streamr_create_message_dictsrKcreate_create_chat_result rrrTrr stream_iter message_dictsrresponses r _generatezChatGroq._generates >>&$,,#@FK( 4 4 $ : :8T J v   &4;;%%G}GG''11rc K|jr)|j|f||d|}t|d{S|j||\}}i||}|jj dd|i|d{}|j |S7V7wr)rf_astreamrrrLrrrs r _ageneratezChatGroq._agenerates >>'$--#@FK/{;; ; $ : :8T J v   2**11S=SFSS''11<Ts"1BB AB4B 5B Bc+\K|j||\}}i||ddi}t}|jjd d|i|D]}t |t s|j }t|ddk(r5|dd} t||} i} | jdx} r,| | d<|j| d<|jdx} r| | d<| jd }|r|| d <| j}t| | xsd }|r|j|j|| |yw) NstreamTrchoicesr finish_reasonrPsystem_fingerprintlogprobsmessagegeneration_info)chunkrr)rrrKrrr model_dumplen_convert_chunk_to_message_chunkrrrPrr4on_llm_new_tokentextrrrTrrrrdefault_chunk_classrchoice message_chunkrrrrgeneration_chunks rrzChatGroq._stream sh!% : :8T J v5F5f5h56D'T[[''II&I #EeT*((*5#$)9%a(F;ECVWM O & ? ;;};3@004 -).3G)HH%HGz'9=*B +0CQ G $0%2$/OO& }(D%*&#1IJOS .1*o +  /C   s #' $*'//"*,,/CR"H kjIIrcj|j}|||d<|Dcgc] }t|}}||fScc}w)NrT)r_convert_message_to_dict)rrrTrmrs rrzChatGroq._create_message_dictssH%%  !F6N>FG1!4G Gf$$Hs0ci}d}|D]Q}||d}|1|jD]\}}||vr|||xx|z cc<|||< |A|jd}S||jd}|r||d<|S)Nrr)rrP)itemsrrrP) r llm_outputsoverall_token_usageroutputrkvcombineds r_combine_llm_outputszChatGroq._combine_llm_outputss$&!! FF~ /K&'--/3DAq//AM+A.!3.12+A. 3 ")%+ZZ0D%E" F$7dooV -?H) *rz0.2.1z.langchain_groq.chat_models.ChatGroq.bind_toolsz1.0.0)since alternativeremovalc f|Dcgc] }t|}}|t|tr|dvrd|in|}t|trt |dk7r t dt|tr&|dd|dk7rt d|d|dddi|d |i}t |d d |i|Scc}w) aBind functions (and other objects) to this chat model. Model is compatible with OpenAI function-calling API. NOTE: Using bind_tools is recommended instead, as the `functions` and `function_call` request parameters are officially deprecated. Args: functions: A list of function definitions to bind to this chat model. Can be a dictionary, pydantic model, or callable. Pydantic models and callables will be automatically converted to their schema dictionary representation. function_call: Which function to require the model to call. Must be the name of the single provided function or "auto" to automatically determine which function to call (if any). **kwargs: Any additional parameters to pass to :meth:`~langchain_groq.chat_models.ChatGroq.bind`. )autononenamergzGWhen specifying `function_call`, you must provide exactly one function.rzFunction call z3 was specified, but the only provided function was . function_call functionsr)r=rrOrrrtrbind)rrrrfnformatted_functionsrs rbind_functionszChatGroq.bind_functionss BIRR"9"=RR  $mS1!)99'#  -.37J3Kq3P   =$/'*62mF6KK $]O4--@-CF-K,LAO@??Fw| )   -SsB.) tool_choicec F|Dcgc] }t|}}|q|ro|dk(rd}t|tr |dvrdd|id}t|tr8t |dkDrt dt |d |d dd}dd|id}||d <t |d d |i|Scc}w)aDBind tool-like objects to this chat model. Args: tools: A list of tool definitions to bind to this chat model. Supports any tool definition handled by :meth:`langchain_core.utils.function_calling.convert_to_openai_tool`. tool_choice: Which tool to require the model to call. Must be the name of the single provided function, "auto" to automatically determine which function to call with the option to not call any function, "any" to enforce that some function is called, or a dict of the form: {"type": "function", "function": {"name": <>}}. **kwargs: Any additional parameters to pass to the :class:`~langchain.runnable.Runnable` constructor. anyrequired)rrrfunctionr)rrrgz>tool_choice can only be True when there is one tool. Received z tools.rrtoolsr)r>rrOrerrtrr)rrrrtoolformatted_tools tool_namers r bind_toolszChatGroq.bind_toolss2EJJD1$7JJ  "{e#( +s+#??'1 ?TU +t,u:>$Xu:,g/,A.z:6B &!' 3 %0F= !w| 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: schema=Pydantic class, method="function_calling", include_raw=True: .. code-block:: python from langchain_groq import ChatGroq from pydantic import BaseModel class AnswerWithJustification(BaseModel): '''An answer to the user question along with justification for the answer.''' answer: str justification: str llm = ChatGroq(model="llama-3.1-405b-reasoning", temperature=0) 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: schema=TypedDict class, method="function_calling", include_raw=False: .. code-block:: python # IMPORTANT: If you are using Python <=3.8, you need to import Annotated # from typing_extensions, not from typing. from typing_extensions import Annotated, TypedDict from langchain_groq import ChatGroq class AnswerWithJustification(TypedDict): '''An answer to the user question along with justification for the answer.''' answer: str justification: Annotated[ Optional[str], None, "A justification for the answer." ] llm = ChatGroq(model="llama-3.1-405b-reasoning", temperature=0) structured_llm = llm.with_structured_output(AnswerWithJustification) 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.' # } Example: schema=OpenAI function schema, method="function_calling", include_raw=False: .. code-block:: python from langchain_groq import ChatGroq oai_schema = { 'name': 'AnswerWithJustification', 'description': 'An answer to the user question along with justification for the answer.', 'parameters': { 'type': 'object', 'properties': { 'answer': {'type': 'string'}, 'justification': {'description': 'A justification for the answer.', 'type': 'string'} }, 'required': ['answer'] } } llm = ChatGroq(model="llama-3.1-405b-reasoning", temperature=0) structured_llm = llm.with_structured_output(oai_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.' # } Example: schema=Pydantic class, method="json_mode", include_raw=True: .. code-block:: from langchain_groq import ChatGroq from pydantic import BaseModel class AnswerWithJustification(BaseModel): answer: str justification: str llm = ChatGroq(model="llama-3.1-405b-reasoning", temperature=0) structured_llm = llm.with_structured_output( AnswerWithJustification, method="json_mode", include_raw=True ) structured_llm.invoke( "Answer the following question. " "Make sure to return a JSON blob with keys 'answer' and 'justification'. " "What's heavier a pound of bricks or a pound of feathers?" ) # -> { # 'raw': AIMessage(content='{ "answer": "They are both the same weight.", "justification": "Both a pound of bricks and a pound of feathers weigh one pound. The difference lies in the volume and density of the materials, not the weight." }'), # 'parsed': AnswerWithJustification(answer='They are both the same weight.', justification='Both a pound of bricks and a pound of feathers weigh one pound. The difference lies in the volume and density of the materials, not the weight.'), # 'parsing_error': None # } Example: schema=None, method="json_mode", include_raw=True: .. code-block:: structured_llm = llm.with_structured_output(method="json_mode", include_raw=True) structured_llm.invoke( "Answer the following question. " "Make sure to return a JSON blob with keys 'answer' and 'justification'. " "What's heavier a pound of bricks or a pound of feathers?" ) # -> { # 'raw': AIMessage(content='{ "answer": "They are both the same weight.", "justification": "Both a pound of bricks and a pound of feathers weigh one pound. The difference lies in the volume and density of the materials, not the weight." }'), # 'parsed': { # 'answer': 'They are both the same weight.', # 'justification': 'Both a pound of bricks and a pound of feathers weigh one pound. The difference lies in the volume and density of the materials, not the weight.' # }, # 'parsing_error': None # } strictNzReceived unsupported arguments json_schemar zJschema must be specified when method is 'function_calling'. Received None.rrr)rschema)rls_structured_output_formatT)rfirst_tool_only)key_namer json_moderr)rr)pydantic_objectz\Unrecognized method argument. Expected one of 'function_calling' or 'json_mode'. Received: ''rawcyNr_s rz1ChatGroq.with_structured_output..,r)parsed parsing_errorcyrrrs rrz1ChatGroq.with_structured_output...r r)r!r") exception_key)r)rwrt_is_pydantic_classr>r r0r/rr-r,r8assignrwith_fallbacksr7)rrrrrris_pydantic_schemaformatted_toolr llm output_parser parser_assign parser_noneparser_with_fallbacks rwith_structured_outputzChatGroq.with_structured_outputs| JJx & >vhGH H/7 ] "(F ' '~ %4F;N&z26:I//%');<,-"C"2E!($(3 !9&! { "))!' 7'5$-C&%V<%'  ++1(!5  /66!%(=8M.44NKK#0#?#? _$@$ 3'*>> >& &r)r{rVreturnr)r0rE)r0zDict[str, str])r0re)r0rOr)rTOptional[List[str]]rrr0r)rrerzHOptional[Union[CallbackManagerForLLMRun, AsyncCallbackManagerForLLMRun]]rrr0re)NN) rList[BaseMessage]rTr1r"Optional[CallbackManagerForLLMRun]rrr0r5) rr2rTr1r'Optional[AsyncCallbackManagerForLLMRun]rrr0r5) rr2rTr1rr3rrr0zIterator[ChatGenerationChunk]) rr2rTr1rr4rrr0z"AsyncIterator[ChatGenerationChunk])r0rV)rzUnion[dict, BaseModel]r0r5)rr2rTr1r0z+Tuple[List[Dict[str, Any]], Dict[str, Any]])rzList[Optional[dict]]r0r)rDSequence[Union[Dict[str, Any], Type[BaseModel], Callable, BaseTool]]rzL.>V(-QU)V)L%N#((?D*Q$M=!& t<!J EJIEOAK<It/ AsJA $J $/6:O3:7;M4;%)K!( *.'.SL(#$2'"*#*^00 +/':= .  "" "" "*%):> 2#2"28 2  2  2.%)?C 2#2"2= 2  2  20%):> %##%#"%#8 %#  %# ' %#T%)?C )##)#")#= )#  )# , )#\  J@%)%1D% 4%*D  5 W5  5  5  35  5 z  .=S.= .=.= 3.=d:>\'\'rrHc<t|txr t|Sr)rrr?)objs rr%r%7s c4 ?%:3%??rceZdZUded<y) _FunctionCallrOrN)r7r8r9r;rrrrCrC;s IrrCct|tr|j|jd}nt|trd|jd}nat|t rd|jd}d|j vr|j d|d<|ddk(rd|d<|js |jrK|jDcgc] }t|c}|jDcgc] }t|c}z|d<nd|j vr|j d|d<|ddk(rd|d<nt|trd |jd}ndt|trd |j|jd }n9t|trd |j|jd }nt!d|d|j vr|j d|d<|Scc}wcc}w)zConvert a LangChain message to a dictionary. Args: message: The LangChain message. Returns: The dictionary. )rolecontentuser assistantrrFrN tool_callssystemr)rErFrr )rErF tool_call_idzGot unknown type r)rr rErFr$radditional_kwargsrIinvalid_tool_calls_lc_tool_call_to_groq_tool_call'_lc_invalid_tool_call_to_groq_tool_callr'r"rr*rK TypeError)r message_dicttcs rrrBs';' ' I G\ * &7??C GY ' +H g77 7,3,E,Eo,VL )I&",*. Y'   !;!;>E>P>P*8:/3*"448;*L & W66 6)0)B)B<)PL &I&",*. Y' G] + (W__E G_ -LL G[ )#00 +G9566 ***&88@ V ;*s ?G!Gc`|dd}|d}tt|jd}tt|jdxsd}i}|jdr!t|d}d|vr |dd|d<||d<|jd r|d |d <|d k(s |tk(r t | S|d k(s |t k(rt|jd xsijdx}r>|jdd} |jdd} | | |jd| | zd} nd} t ||| S|dk(s |t k(r t | S|dk(s |tk(rt||dS|dk(s |tk(rt||dS|s |tk(r t||S|| S)NrrdeltarErFrrrrIrGrFrHx_groqrrrrr)rFrLrrJrrFrr rK)rFrKrFrE) rrOrrrr%rr(r#r+r!) r default_classr_dictrErFrLrrrrrs rrrxs9 a F 7OE UYYv& 'D3 ),23G  yy!U?34 ] "}V'<'D$&M& !-:/* yy*/ *=,' v~*;; 11    ?YYx(.B33G< <5 < 99_a8L!II&91=M ,!. % .,:V WN "N/)   ].@@!'22  }0DD#G%-HH =,<<eN>STT "22d;;W--rc x|jd}|jd}|dk(rt|jddS|dk(r|jddxsd}i}|jdx}rt||d<g}g}|jd x}r)||d <|D]} |jt | d !t||||| S|dk(rt|jddS|dk(r,t|jdd|jdS|dk(r;i}d|vr|d|d<t|jdd|jd|St|jdd|S#t $r/} |jt | t| Yd } ~ d } ~ wwxYw)zConvert a dictionary to a LangChain message. Args: _dict: The dictionary. Returns: The LangChain message. idrErGrFrrUrHrrIT) return_idN)rFr\rLrIrMrJrrrWr rK)rFrKrLrX) rrr$rrr2 Exceptionr1rOrr'r"r*r ) rZid_rErFrLrrIrMraw_tool_calls raw_tool_calles rrrs ))D/C 99V D v~EIIi$<==  ))Ir*0b"$!IIo6 6= 615m1D o . "YY|4 4> 4.< l +!/  %%omt&TU /!1     UYYy"%=>>  uyyB'?eiiPVFWXX  U?(-f f %IIi,>2/  599Y#;$GG3!&--.}c!fEs$F F9 $F44F9cLd|d|dtj|dddSNrr\rargs)r arguments)rr\r)jsondumps) tool_calls rrNrNs4of%If$56  rc&d|d|d|dddSrdr)invalid_tool_calls rrOrOs.%%f-*62  r)rArr0re)rrr0r)rMapping[str, Any]rYzType[BaseMessageChunk]r0r)rZrlr0r)rir)r0r)rkr&r0r)cr: __future__rrgruoperatorrtypingrrrrr r r r r rrrrrrlangchain_core._apirlangchain_core.callbacksrrlangchain_core.language_modelsr*langchain_core.language_models.chat_modelsrrrrlangchain_core.messagesrrrrr r!r"r#r$r%r&r'r(r)r*r+langchain_core.output_parsersr,r-"langchain_core.output_parsers.baser.*langchain_core.output_parsers.openai_toolsr/r0r1r2langchain_core.outputsr3r4r5langchain_core.runnablesr6r7r8langchain_core.toolsr9langchain_core.utilsr:r;r<%langchain_core.utils.function_callingr=r>langchain_core.utils.pydanticr?pydanticr@rArBrCrDtyping_extensionsrElangchain_groq.versionrFrHr%rCrrrrNrOrrrrs" $+> $@ SROO) @#.X'}X'v@I3l+. +.-C+.+.\2Hj &   r