j kddlmZddlZddlZddlmZmZmZddlm Z m Z m Z m Z m Z ddlZddlZddlmZddlmZddlmZmZmZddlmZmZmZmZmZdd lmZej@e!Z" d d Z#Gd d eeZ$y)) annotationsN)IterableMappingSequence)AnyLiteralOptionalUnioncast) Embeddings)run_in_executor)from_envget_pydantic_field_namessecret_from_env) BaseModel ConfigDictField SecretStrmodel_validator)Selfc  t|Dcgc]}g}}t|Dcgc]}g}}tt|D]S}|rt||dk(r|||j|||||jt||Ug} t|D]}||} t| dk(r| jd(t| dk(r| j| dKt||} t | D cgc]$} tdt | ||D| z &} } td| Ddz}| j| Dcgc]}||z  c}| Scc}wcc}wcc} wcc}w)Nrc3,K|] \}}||zywN).0valweights j/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain_openai/embeddings/base.py z6_process_batched_chunked_embeddings..@s 'M V&L'Msc3&K|] }|dz yw)Nr)rrs rr z6_process_batched_chunked_embeddings..Js6gsCFgg?)rangelenappendsumzip) num_textstokensbatched_embeddingsindices skip_empty_resultsnum_tokens_in_batchi embeddings_result total_weight embeddingaverage magnituders r#_process_batched_chunked_embeddingsr8s5:)4D'E4Dq4DG'E 9>i8H+I8H1B8H+I 3w<  #0349  ""#5a#89GAJ'..s6!9~> !/1J 9 %,QZ w<1    d #  \Q    gaj )  2156L"%g  "/I '*96I!6L'M  "/ 6g66#=I   'B'3sY'B CAD c(F ,J<Cs E1 E6 )E; F ceZdZUdZeddZded<eddZded<dZd ed <dZ d ed < eZ d ed<ee dddZ d ed< ede ddZ d ed< ee ddZd ed<ee ddZd ed<dZded< ed ed!dZd"ed#< ed$e d%d&gdZd ed'< dZd(ed)<dZd*ed+<d,Zded-< d.Zded/< edd01Zd2ed3< dZded4<dZd5ed6< dZd ed7< d8Zd5ed9< eeZd:ed;< d8Zd5ed<< dZ d=ed><dZ!d?ed@<dAZ"dedB< dCZ#dedD< dZ$dEedF< dZ%dEedG< dZ&d5edH< e'dIddJKZ(e)dLMe*dZdNZ+e)dOMd[dPZ,e-d\dQZ. d]dRZ/ddS d^dTZ0ddS d^dUZ1 d_ d`dVZ2 d_ d`dWZ3dadXZ4dadYZ5y)bOpenAIEmbeddingsu OpenAI embedding model integration. Setup: Install ``langchain_openai`` and set environment variable ``OPENAI_API_KEY``. .. code-block:: bash pip install -U langchain_openai export OPENAI_API_KEY="your-api-key" Key init args — embedding params: model: str Name of OpenAI model to use. dimensions: Optional[int] = None The number of dimensions the resulting output embeddings should have. Only supported in ``'text-embedding-3'`` and later models. Key init args — client params: api_key: Optional[SecretStr] = None OpenAI API key. organization: Optional[str] = None OpenAI organization ID. If not passed in will be read from env var ``OPENAI_ORG_ID``. max_retries: int = 2 Maximum number of retries to make when generating. request_timeout: Optional[Union[float, Tuple[float, float], Any]] = None Timeout for requests to OpenAI completion API See full list of supported init args and their descriptions in the params section. Instantiate: .. code-block:: python from langchain_openai import OpenAIEmbeddings embed = OpenAIEmbeddings( model="text-embedding-3-large" # With the `text-embedding-3` class # of models, you can specify the size # of the embeddings you want returned. # dimensions=1024 ) Embed single text: .. code-block:: python input_text = "The meaning of life is 42" vector = embeddings.embed_query("hello") print(vector[:3]) .. code-block:: python [-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915] Embed multiple texts: .. code-block:: python vectors = embeddings.embed_documents(["hello", "goodbye"]) # Showing only the first 3 coordinates print(len(vectors)) print(vectors[0][:3]) .. code-block:: python 2 [-0.024603435769677162, -0.007543657906353474, 0.0039630369283258915] Async: .. code-block:: python await embed.aembed_query(input_text) print(vector[:3]) # multiple: # await embed.aembed_documents(input_texts) .. code-block:: python [-0.009100092574954033, 0.005071679595857859, -0.0029193938244134188] NT)defaultexcluderclient async_clientztext-embedding-ada-002strmodel Optional[int] dimensionsz Optional[str] deploymentOPENAI_API_VERSION)r; api_version)default_factoryaliasopenai_api_versionbase_urlOPENAI_API_BASE)rGrFopenai_api_baseOPENAI_API_TYPE)rFopenai_api_type OPENAI_PROXY openai_proxyiintembedding_ctx_lengthapi_keyOPENAI_API_KEYzOptional[SecretStr]openai_api_key organization OPENAI_ORG_IDOPENAI_ORGANIZATIONopenai_organizationz%Union[Literal['all'], set[str], None]allowed_specialz4Union[Literal['all'], set[str], Sequence[str], None]disallowed_speciali chunk_sizer" max_retriestimeout)r;rGz0Optional[Union[float, tuple[float, float], Any]]request_timeoutheadersbooltiktoken_enabledtiktoken_model_nameFshow_progress_bardict[str, Any] model_kwargsr-zUnion[Mapping[str, str], None]default_headersz!Union[Mapping[str, object], None] default_queryretry_min_secondsretry_max_secondszUnion[Any, None] http_clienthttp_async_clientcheck_embedding_ctx_lengthforbidr)extrapopulate_by_nameprotected_namespacesbefore)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.rezFound 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.) rgetlist ValueErrorwarningswarnpop intersectionkeys)clsvaluesall_required_field_namesrp field_nameinvalid_model_kwargss r build_extrazOpenAIEmbeddings.build_extras$2.v,JU" 6*5E!FGG!99 !*.L!))3 4JN %+JJz$:j!' 8DDUZZ\R 234ST  "'~ afterc4|jdvr td|jr|jjnd|j|j |j |j|j|jd}|jrP|js |jr8|j}|j}|j}td|d|d||jsr|jr2|js& ddl}|j!|j |_ d |ji}t#j$d i||j&|_ |j(sr|jr2|js& ddl}|j+|j |_ d |ji}t#j,d i||j&|_|S#t$r}td |d}~wwxYw#t$r}td |d}~wwxYw) z?Validate that api key and python package exists in environment.)azureazure_adazureadzEIf you are using Azure, please use the `AzureOpenAIEmbeddings` class.N)rRrUrIr]r\rfrgzwCannot specify 'openai_proxy' if one of 'http_client'/'http_async_client' is already specified. Received: openai_proxy=z http_client=z http_async_client=rzRCould not import httpx python package. Please install it with `pip install httpx`.)proxyrlr)rMrxrTget_secret_valuerXrKr^r\rfrgrOrlrmr=httpx ImportErrorClientopenaiOpenAIr2r> AsyncClient AsyncOpenAI) self client_paramsrOrlrmre sync_specificasync_specifics rvalidate_environmentz%OpenAIEmbeddings.validate_environment!s*   #C CW  ;?:M:M##446SW 44,,++++#33!//     $"2"2d6L6L,,L**K $ 6 6 !/K>1F4E3GI  {{  )9)9 $)<.%O>Na n>Nr#dataNcIjjdddi}t|ts|j }|dddSNrrrr5r)r=create isinstancedict model_dumpaverage_embedded_cached_empty_embedding client_kwargsrs rempty_embeddingzBOpenAIEmbeddings._get_len_safe_embeddings..empty_embeddings]&.#54;;#5#5#PB#P-#P !"2D9'7'B'B'D$*:6*B1*Ek*R'* *rrreturn list[float]) r[rrr=rrrrextendr8r%r-rrenginer[kwargs _chunk_sizerr*r,r+r1responser2rrrrs` @@r_get_len_safe_embeddingsz)OpenAIEmbeddings._get_len_safe_embeddingss.!3DOO =422=f= !%{!Cvw02A)t{{))Q[15BHh-#..0  % %%Ohv>N%O O 9 J 2GT__ :> +DNN:aQ](99:NNNsC'c PK|xs j}ij|tdj||d{\}}}g} t dt ||D]i} j jdd|| | |zid{} t| ts| j} | jd| dDktt ||| |j} ddfd } | Dcgc]}||n| d{c}S777 cc}ww) a Asynchronously generate length-safe embeddings for a list of texts. This method handles tokenization and asynchronous embedding generation, respecting the set embedding context length and chunk size. It supports both `tiktoken` and HuggingFace `tokenizer` based on the tiktoken_enabled flag. Args: texts (List[str]): A list of texts to embed. engine (str): The engine or model to use for embeddings. chunk_size (Optional[int]): The size of chunks for processing embeddings. Returns: List[List[float]]: A list of embeddings for each input text. Nrrc3&K|] }|d ywrrrs rr z=OpenAIEmbeddings._aget_len_safe_embeddings..rr#rcKQjjdddid{}t|ts|j }|dddS71wr)r>rrrrrs rrzCOpenAIEmbeddings._aget_len_safe_embeddings..empty_embedding$sw&.)A):):)A)A** -*$ ""2D9'7'B'B'D$*:6*B1*Ek*R'* * $s$AA2Arr)r[rr rr$r%r>rrrrrr8r-rs` @@r_aget_len_safe_embeddingsz*OpenAIEmbeddings._aget_len_safe_embeddingssC0!3DOO =422=f= '6 $..%( " vw13q#f+{3A5T..55Q[15BHh-#..0  % %%Ohv>N%O O49 J 2GT__ :> +JTTAQ]o.?(??TT;" 0)@TsID!D D!D&D&D!!D&c |xs |j}i|j|}|js~g}tdt ||D]a}|j j dd||||zi|}t|ts|j}|jd|dDc|Stt|j} |j|f| |d|S)aCall out to OpenAI's embedding endpoint for embedding search docs. Args: texts: The list of texts to embed. chunk_size: The chunk size of embeddings. If None, will use the chunk size specified by the class. kwargs: Additional keyword arguments to pass to the embedding API. Returns: List of embeddings, one for each text. rrc3&K|] }|d ywrrrs rr z3OpenAIEmbeddings.embed_documents..I!K:JQ!K.:Jr#rrr[r)r[rrnr$r%r=rrrrrr r?rCr rrr[r chunk_size_rr2r1rrs rembed_documentsz OpenAIEmbeddings.embed_documents1s!3DOO =422=f= ..,.J1c%j+6-4;;--A O48E"(D1'224H!!!K(6:J!KK 7 c4??+,t,,   Z ;A  rc K|xs |j}i|j|}|jsg}tdt ||D]i}|j j dd||||zi|d{}t|ts|j}|jd|dDk|Stt|j} |j|f| |d|d{S7{7w)aCall out to OpenAI's embedding endpoint async for embedding search docs. Args: texts: The list of texts to embed. chunk_size: The chunk size of embeddings. If None, will use the chunk size specified by the class. kwargs: Additional keyword arguments to pass to the embedding API. Returns: List of embeddings, one for each text. rrNc3&K|] }|d ywrrrs rr z4OpenAIEmbeddings.aembed_documents..krr#rrr)r[rrnr$r%r>rrrrrr r?rCrrs raembed_documentsz!OpenAIEmbeddings.aembed_documentsSs!3DOO =422=f= ..,.J1c%j+6!9!2!2!9!9"A O4"8E""(D1'224H!!!K(6:J!KK 7 c4??+3T33   Z ;A    s%A/C11C-2A6C1(C/)C1/C1c 0|j|gfi|dS)aCall out to OpenAI's embedding endpoint for embedding query text. Args: text: The text to embed. kwargs: Additional keyword arguments to pass to the embedding API. Returns: Embedding for the text. r)r)rrrs r embed_queryzOpenAIEmbeddings.embed_queryus#$t##TF5f5a88rcPK|j|gfi|d{}|dS7 w)a Call out to OpenAI's embedding endpoint async for embedding query text. Args: text: The text to embed. kwargs: Additional keyword arguments to pass to the embedding API. Returns: Embedding for the text. Nr)r)rrrr2s r aembed_queryzOpenAIEmbeddings.aembed_querys41400$B6BB !}Cs &$ &)rrdrr)rr)rrd)r list[str]r[rPrzr@rBrCrrHrKrMrOrQrrTrXrYrZr[r\r^r_rarbrcrrer-rfrgrirkrlrmrnr model_configr classmethodrrpropertyrrrrrrrrrrrr:r:PsPdd3FC3dD9L#9)E3) $J $ !&J %(- !5tD) T%*(3Dd*S&O]&+ !2DA&O]#( >#L-!%#$8*/9ISW)X+N'R). 3 4d * Q=AO:AOSLSJ8KL.>VJ!6:O3:7;M4;s7s7$(K!(+/'.W'++-BL(#$2'"6#6p ^&^&,/^& E^&N%) 1O1O 1O " 1O  1O 1Ot%) 7U7U 7U " 7U  7U 7Ut=A    ,9  LO    F=A    ,9  LO    D 9 rr:) r)rPr*zlist[Union[list[int], str]]r+rr,z list[int]r-r`rzlist[Optional[list[float]]])% __future__rloggingrycollections.abcrrrtypingrrr r r rrlangchain_core.embeddingsr langchain_core.runnables.configr langchain_core.utilsrrrpydanticrrrrrtyping_extensionsr getLoggerrloggerr8r:rrrrs"7766 0;TTMM"   8 $:: ':*: :  : ! :z|y*|r