dh[zSSKrSSKJrJrJrJrJrJrJr SSK r SSK J r SSK J r SSKJr SSKJrJr SSKJrJr SSK Jr "S S \ 5r"S S \ 5rg) N)AnyDictIteratorListOptionalTupleUnion)CallbackManagerForLLMRun)LLM)GenerationChunk)convert_to_secret_strget_from_dict_or_env)Field SecretStr)Responsec ^\rSrSr%Sr\"SS9r\\S'\"\ "S5S9r \ \S'\"SSS9r \\S '\"SSS9r \\S '\"S S9r \\S 'S r\\\\4\S'"SS5r\S\4Sj5r\S\\\44Sj5r\S\\\44Sj5r\S\4Sj5rS\SS 4U4SjjrS\S\\\44SjrS%S\\\S\\\44SjjrS&S\\\\4S\\\S \\S\ 4Sjjr!S\ S\4Sjr"S\ S\#\$4S jr%S'S\\\\4S\\\S!\\&S\S\#\$4 S"jjr'S'S\\\\4S\\\S!\\&S\S\4 S#jjr(S$r)U=r*$)( SambaStudio ua SambaStudio large language models. Setup: To use, you should have the environment variables ``SAMBASTUDIO_URL`` set with your SambaStudio environment URL. ``SAMBASTUDIO_API_KEY`` set with your SambaStudio endpoint API key. https://sambanova.ai/products/enterprise-ai-platform-sambanova-suite read extra documentation in https://docs.sambanova.ai/sambastudio/latest/index.html Example: .. code-block:: python from langchain_community.llms.sambanova import SambaStudio SambaStudio( sambastudio_url="your-SambaStudio-environment-URL", sambastudio_api_key="your-SambaStudio-API-key, model_kwargs={ "model" : model or expert name (set for Bundle endpoints), "max_tokens" : max number of tokens to generate, "temperature" : model temperature, "top_p" : model top p, "top_k" : model top k, "do_sample" : wether to do sample "process_prompt": wether to process prompt (set for Bundle generic v1 and v2 endpoints) }, ) Key init args — completion params: model: str The name of the model to use, e.g., Meta-Llama-3-70B-Instruct-4096 (set for Bundle endpoints). streaming: bool Whether to use streaming handler when using non streaming methods model_kwargs: dict Extra Key word arguments to pass to the model: max_tokens: int max tokens to generate temperature: float model temperature top_p: float model top p top_k: int model top k do_sample: bool wether to do sample process_prompt: wether to process prompt (set for Bundle generic v1 and v2 endpoints) Key init args — client params: sambastudio_url: str SambaStudio endpoint Url sambastudio_api_key: str SambaStudio endpoint api key Instantiate: .. code-block:: python from langchain_community.llms import SambaStudio llm = SambaStudio=( sambastudio_url = set with your SambaStudio deployed endpoint URL, sambastudio_api_key = set with your SambaStudio deployed endpoint Key, model_kwargs = { "model" : model or expert name (set for Bundle endpoints), "max_tokens" : max number of tokens to generate, "temperature" : model temperature, "top_p" : model top p, "top_k" : model top k, "do_sample" : wether to do sample "process_prompt" : wether to process prompt (set for Bundle generic v1 and v2 endpoints) } ) Invoke: .. code-block:: python prompt = "tell me a joke" response = llm.invoke(prompt) Stream: .. code-block:: python for chunk in llm.stream(prompt): print(chunk, end="", flush=True) Async: .. code-block:: python response = llm.ainvoke(prompt) await response defaultsambastudio_urlsambastudio_api_keyT)rexcludebase_url streaming_urlF streamingN model_kwargsc\rSrSrSrSrg)SambaStudio.Config|TN__name__ __module__ __qualname____firstlineno__populate_by_name__static_attributes__r"Z/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/llms/sambanova.pyConfigr |r*r,returncg)9Return whether this model can be serialized by Langchain.Tr"clss r+is_lc_serializableSambaStudio.is_lc_serializablesr*c SSS.$)Nrr)rrr"selfs r+ lc_secretsSambaStudio.lc_secretss 1#8  r*c:SUR0SUR0E$)Return a dictionary of identifying parameters. This information is used by the LangChain callback system, which is used for tracing purposes make it possible to monitor LLMs. rr)rrr6s r+_identifying_paramsSambaStudio._identifying_paramss#T^^S@Q@Q/RSSr*cg)zReturn type of llm.zsambastudio-llmr"r6s r+ _llm_typeSambaStudio._llm_types!r*kwargsc >[USS5US'[[USS55US'URUS5uUS'US'[TU]"S0UD6 g) 'init and validate environment variablesrSAMBASTUDIO_URLrSAMBASTUDIO_API_KEYrrNr")rr _get_sambastudio_urlssuper__init__r7rA __class__s r+rHSambaStudio.__init__sx$8 %'8%  !)> )>@U V) $%7;6P6P $ %7 3zF?3 "6"r*urlcSU;aUnUnX#4$SU;aURSS5nUnX#4$UnSU;a#SRURS55nX#4$[S5e)z Get streaming and non streaming URLs from the given URL Args: url: string with sambastudio base or streaming endpoint url Returns: base_url: string with url to do non streaming calls streaming_url: string with url to do streaming calls chat/completionsstreamzstream/rgenericzgeneric/streamUnsupported URL)replacejoinsplit ValueError)r7rLr stream_urls r+rF!SambaStudio._get_sambastudio_urlss  $HJ##3;;y"5 ## #!1!6!6syy7K!LJ##%%677r*stopc Uc/nUR=(d 0nURS/5U-n[U5S:aX2S'SUR;aySUR 5;aUR S5US'SUR 5;aUR S5US'SUR 5;aUR S5 UnU$S UR;aTSUR 5;aUR S5US'SUR 5;aUR S5US'UnU$S UR;aSUR 5;aUR S5US'SUR 5;aUR S5US'UR 5VVs0sH'upVU[U5R[U5S ._M) nnnU$[S URS 35es snnf)a  Get the tuning parameters to use when calling the LLM. Args: stop: Stop words to use when generating. Model output is cut off at the first occurrence of any of the stop substrings. Returns: The tuning parameters in the format required by api to use stop_sequencesrrN select_expertmodelmax_tokens_to_generate max_tokensprocess_promptapi/v2/predict/genericapi/predict/generic)typevaluerQ9only openai, generic v1 and generic v2 APIs are supported) rgetlenrkeyspopitemsrbr$strrU)r7rX _model_kwargs_stop_sequences tuning_paramskvs r+_get_tuning_paramsSambaStudio._get_tuning_paramss% <D))/R (++,1B1B71K o.}1133:G:K:K ; 67*M*'#d&:&: :-,,..1>1B1B71K o.}1133:G:K:K ; 67 +0022DADG,,s1v>>2  !$"6"6!7KL  s#-G.promptc[U[5(aU/nURU5nSUR;aYSUSS./nXSS.UEnUR 5VVs0sH upxUcM Xx_M nnnSUR R 53SS .n GOQS UR;aURS S 5(a"[R"S SSUSS./S.5nOUSnSUS./n UR 5VVs0sH upxUcM Xx_M nnnXS.nSUR R 50n OSUR;aURS S 5(a@US RS5S:Xa"[R"S SSUSS./S.5nO USnOUSnU(aXS.nOU/US.nSUR R 50n O[SURS35e[R"5n U(aU RURXSS9n OU RURXS S9n U R S:wa&[#SU R SU R$S35eU $s snnfs snnf) z Performs a post request to the LLM API. Args: prompt: The prompt to pass into the model stop: list of stop tokens streaming: wether to do a streaming call Returns: A request Response object rNuserrrolecontent)messagesrONBearer application/json Authorizationz Content-Typer`r_Fzsambaverse-conversation-id) message_idrvrw)conversation_idrxitem0)idrc)riparamskeyrarcTrue)instancer) instancesrrQrdTheadersjsonrO2Sambanova / complete call failed with status code .) isinstancerjrprrirget_secret_valuererdumpsrUrequestsSessionpostrr status_code RuntimeErrortext) r7rrrXrr messages_dictdatarrcrri http_sessionresponses r+_handle_requestSambaStudio._handle_requests$ fc " "XF((. !5!5 5&,CDM -MfMD15S:3JCJDS#*++<<>?"A 2G&)=)= =zz*E22+G+/FSTIV% #f56E39<<>W>ZSUjcj>FW"5Dd66GGIJG#d&:&: :zz*E22*+//8FB!ZZ/K37,2/5ay!")  F$AYF$*=&,X@d66GGIJG!$"6"6!7KL   '') #((""Gt)H$(( w%)H   3 &D''(==/$  ST*XsI/(I/:I5I5rcjUR5nSUR;aUSSSSnU$S UR;aUS SS S nU$S UR;a USSS nU$[ SURS35e![a n[SUSUR35eSnAff=f) Process a non streaming response from the api Args: response: A request Response object Returns completion: a string with model generation ;Sambanova /complete call failed couldn't get JSON response response: NrNchoicesrmessagerwr`rirc completionra predictionsrQrd)r ExceptionrrrrUr7r response_dicters r+_process_responseSambaStudio._process_responsehs $MMOM !5!5 5&y1!4Y? JJ&)=)= =&w/27;LIJ#d&:&: :&}5a8FJ  !$"6"6!7KL ! MaSX]]O-  sB B2B--B2c#|# SSKnSUR;GaGURU5nUR 5GH nUR S:Xa&[ SURSURS35eURS:wa[UR[5(a![R"UR5nO&[ SURSURS35eURS 5(a&[ SURSURS35e[US 5S:aUS SS S nOS n[US9nUv GM GM# gSUR;aMUR#5H8n [R"U 5nUSSSSSn[US9nUv M: gSUR;aJUR#5H5n [R"U 5nUSSSSn[US9nUv M7 g[%SURS35e![a [S5ef=f![ a n[ SUSUR35eSnAff=f![ an[ SUSU 35eSnAff=f![ an[ SUSU 35eSnAff=f7f) Process a streaming response from the api Args: response: An iterable request Response object Yields: GenerationChunk: a GenerationChunk with model partial generation rNTcould not import sseclient libraryPlease install it with `pip install sseclient-py`.rN error_event1Sambanova /complete call failed with status code r[DONE]errorrdeltarwrr3Error getting content chunk raw streamed response: data: r`resultrirc stream_tokenzline: ra responsesrQrd) sseclient ImportErrorr SSEClienteventseventrrrrrjrloadsrerfr r iter_linesrU) r7rrclientrrrwgenerated_chunkrlines r+_process_stream_response$SambaStudio._process_stream_responses   !5!5 5((2F;;-/&K#//0 ::,a) zzX-%ejj#66#'::ejj#9D"."S#+#7#7"8#(::,a!1#  88G,,"."S#+#7#7"8#(::,a!1# tI/!3&*9oa&8&A)&LG&(G*9w*G--).)L&)=)= = ++- ::d+D"8nW5a8A.QG&57&CO)) .#d&:&: : ++- ::d+D"8n[9!<^LG&57&CO)) .!$"6"6!7KL [ E  P!&MaS  .!&MaS (!&MaS (sJ<H0A,J<5C"I ,J<4I68(J<!1JJ<0IJ< I3I..I33J<6 JJJJ< J9#J44J99J< run_managerc+# URXSS9nURU5H)nU(aURUR5 Uv M+ g7f)a$Call out to Sambanova's complete endpoint. Args: prompt: The prompt to pass into the model. stop: a list of strings on which the model should stop generating. run_manager: A run manager with callbacks for the LLM. Yields: chunk: GenerationChunk with model partial generation TrNrron_llm_new_tokenrr7rrrXrrArchunks r+_streamSambaStudio._streamK '''E228>JkEKjj(   '''F++H5 r*r")NNFNN)+r$r%r&r'__doc__rrrj__annotations__rrrrrboolrrrrr, classmethodr3propertyr8r<r?rHrrFrrpr rrrrr rr rrr) __classcell__rJs@r+rr sZx!,OS,%*9R=%AA"d3Hc3'r48M38#E*It*K-1L(4S>*12  4 DcN  TT#s(^TT!3!! # # #$$sCx$4?xS ':?d3PS8n?H%)$) dd3in%dtCy!dD> d  dL"("s"H]]h>W]D%):> d3in%tCy!67    / " 2%):> d3in%tCy!67    r*rc ^\rSrSr%Sr\"SS9r\\S'\"\ "S5S9r \ \S'\"SS9r \\S'\"S S9r \ \S '\"S S9r\\S '\"S S9r\\S'\"SS9r\\\S'\"SS9r\\\S'\"SS0S9r\\S'"SS5r\S\ 4Sj5r\S\\\44Sj5r\S\\\44Sj5r\S\4Sj5rS\SS4U4Sjjr S(S\!\"\\4S\\"\S \\ S\#4S jjr$S!\#S\4S"jr%S!\#S\&\'4S#jr(S)S\!\"\\4S\\"\S$\\)S\S\4 S%jjr*S)S\!\"\\4S\\"\S$\\)S\S\&\'4 S&jjr+S'r,U=r-$)*SambaNovaCloudiu SambaNova Cloud large language models. Setup: To use, you should have the environment variables: ``SAMBANOVA_URL`` set with SambaNova Cloud URL. defaults to http://cloud.sambanova.ai/ ``SAMBANOVA_API_KEY`` set with your SambaNova Cloud API Key. Example: .. code-block:: python from langchain_community.llms.sambanova import SambaNovaCloud SambaNovaCloud( sambanova_api_key="your-SambaNovaCloud-API-key, model = model name, max_tokens = max number of tokens to generate, temperature = model temperature, top_p = model top p, top_k = model top k ) Key init args — completion params: model: str The name of the model to use, e.g., Meta-Llama-3-70B-Instruct-4096 (set for CoE endpoints). streaming: bool Whether to use streaming handler when using non streaming methods max_tokens: int max tokens to generate temperature: float model temperature top_p: float model top p top_k: int model top k Key init args — client params: sambanova_url: str SambaNovaCloud Url defaults to http://cloud.sambanova.ai/ sambanova_api_key: str SambaNovaCloud api key Instantiate: .. code-block:: python from langchain_community.llms.sambanova import SambaNovaCloud SambaNovaCloud( sambanova_api_key="your-SambaNovaCloud-API-key, model = model name, max_tokens = max number of tokens to generate, temperature = model temperature, top_p = model top p, top_k = model top k ) Invoke: .. code-block:: python prompt = "tell me a joke" response = llm.invoke(prompt) Stream: .. code-block:: python for chunk in llm.stream(prompt): print(chunk, end="", flush=True) Async: .. code-block:: python response = llm.ainvoke(prompt) await response rr sambanova_urlsambanova_api_keyzMeta-Llama-3.1-8B-Instructr\Frir^gffffff? temperatureNtop_ptop_k include_usageTstream_optionsc\rSrSrSrSrg)SambaNovaCloud.Configi{Tr"Nr#r"r*r+r,r{r-r*r,r.cg)r0Fr"r1s r+r3!SambaNovaCloud.is_lc_serializable~sr*c SS0$)Nrr"r6s r+r8SambaNovaCloud.lc_secretss#%899r*cURURURURURUR UR S.$)r;r\rr^rrrrrr6s r+r<"SambaNovaCloud._identifying_paramssCZZ//++ZZZZ"11  r*cg)z7Get the type of language model used by this chat model.zsambanovacloud-llmr"r6s r+r?SambaNovaCloud._llm_types$r*rAc v>[USSSS9US'[[USS55US'[TU] "S0UD6 g) rCr SAMBANOVA_URLz,https://api.sambanova.ai/v1/chat/completionsrrSAMBANOVA_API_KEYNr")rr rGrHrIs r+rHSambaNovaCloud.__init__sP"6   B #  '< )<>Q R' "# "6"r*rrrXc p[U[5(aU/nSUSS./nUUURUURURUR UR S.nUR5VVs0sH upgUcM Xg_M nnnSURR53SS.n[R"5n U(aU RURXSS 9n OU RURXS S 9n U RS :wa&[S U RS U R S 35eU $s snnf)z Performs a post request to the LLM API. Args: prompt: The prompt to pass into the model. stop: list of stop tokens Returns: A request Response object rtrru)rxrOr^rXr\rrrryrzr{TrFrrr)rrjr^r\rrrrirrrrrrrrr) r7rrrXrrrrrcrrrs r+rSambaNovaCloud._handle_requestsJ fc " "XF"(VAY?@ %//ZZ++ZZZZ  .2ZZ\O\zsU  \O&t'='='N'N'P&QR.   '') #((""Gt)H$((""Gu)H   3 &D''(==/$  -Ps 2D2>D2rcUR5nUSSSSnU$![a n[SUSUR35eSnAff=f)rrrNrrrrw)rrrrrs r+r SambaNovaCloud._process_responsesi $MMOM#9-a0;IF  MaSX]]O-  s" A AA c#.# SSKnURU5nUR5GH nURS:Xa&[ SUR SURS35eURS:wa[UR[5(a![R"UR5nO&[ SUR SURS35eURS5(a&[ SUR SURS35e[US 5S:aUS SS S nOS n[US 9nUv GM GM# g![a [S5ef=f![a n[ SUSUR35eSnAff=f7f)rrNrrrrrrrrrwrrrr)rrrrrrrrrrjrrrerfr r) r7rrrrrrwrrs r+r'SambaNovaCloud._process_stream_responses  $$X.]]_E{{m+"G++,Azzl!%  ::)!%**c22#zz%**5*O'334A$zzl!- xx((*O'334A$zzl!- 4 ?+a/"&y/!"4W"=i"H"$&57&CO)))*% E  L "I!UZZL* sAFEAF$C"E( FE%%F( F2F  FFrc UR(a.SnUR"SXUS.UD6HnXVR- nM U$URXSS9nUR U5nU$)Call out to SambaNovaCloud complete endpoint. Args: prompt: The prompt to pass into the model. stop: Optional list of stop words to use when generating. Returns: The string generated by the model. rrFrr"rrs r+rSambaNovaCloud._call1rr*c+# URXSS9nURU5H)nU(aURUR5 Uv M+ g7f)rTrNrrs r+rSambaNovaCloud._streamNrrr"rr).r$r%r&r'rrrrjrrrr\rrr^intrfloatrrrrdictr,rr3rrr8rr<r?rHr rrrrrr rr rrr)rrs@r+rrs>@r*M3*#(2#?y?!; 4  4l(s077h>W7x%):> d3in%tCy!67    @%):> d3in%tCy!67    / " r*r)rtypingrrrrrrr r langchain_core.callbacks.managerr #langchain_core.language_models.llmsr langchain_core.outputsr langchain_core.utilsr rpydanticrrrrrr"r*r+r sC DDDE32L%O#OdCSCr*