a bg'@sdZddlZddlmZddlmZmZmZmZm Z m Z ddl Z ddl Z ddlZddlmZddlmZddlmZmZmZdgZGd ddeeZGd d d ZdS) z-written under MIT Licence, Michael Feil 2023.N)ThreadPoolExecutor)AnyCallableDictListOptionalTuple) Embeddings)get_from_dict_or_env) BaseModel ConfigDictmodel_validatorInfinityEmbeddingsc@seZdZUdZeed<dZeed<dZeed<e ddZ e d d e e ed d d ZeeeeedddZeeeeedddZeeedddZeeedddZdS)raBSelf-hosted embedding models for `infinity` package. See https://github.com/michaelfeil/infinity This also works for text-embeddings-inference and other self-hosted openai-compatible servers. Infinity is a package to interact with Embedding Models on https://github.com/michaelfeil/infinity Example: .. code-block:: python from langchain_community.embeddings import InfinityEmbeddings InfinityEmbeddings( model="BAAI/bge-small", infinity_api_url="http://localhost:7997", ) modelzhttp://localhost:7997infinity_api_urlNclientZforbid)extrabefore)mode)valuesreturncCs&t|dd|d<t|dd|d<|S)z?Validate that api key and python package exists in environment.rZINFINITY_API_URL)hostr)r &TinyAsyncOpenAIInfinityEmbeddingClient)clsrru/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain_community/embeddings/infinity.pyvalidate_environment3s z'InfinityEmbeddings.validate_environmenttextsrcCs|jj|j|d}|S)zCall out to Infinity's embedding endpoint. Args: texts: The list of texts to embed. Returns: List of embeddings, one for each text. rr)rembedrselfr embeddingsrrrembed_documentsAs z"InfinityEmbeddings.embed_documentscs|jj|j|dIdH}|S)zAsync call out to Infinity's embedding endpoint. Args: texts: The list of texts to embed. Returns: List of embeddings, one for each text. rN)raembedrr!rrraembed_documentsPs  z#InfinityEmbeddings.aembed_documents)textrcCs||gdS)zCall out to Infinity's embedding endpoint. Args: text: The text to embed. Returns: Embeddings for the text. r)r$)r"r'rrr embed_query_s zInfinityEmbeddings.embed_querycs||gIdH}|dS)zAsync call out to Infinity's embedding endpoint. Args: text: The text to embed. Returns: Embeddings for the text. Nr)r&)r"r'r#rrr aembed_queryjs zInfinityEmbeddings.aembed_query)__name__ __module__ __qualname____doc__str__annotations__rrrr Z model_configr classmethodrrrfloatr$r&r(r)rrrrrs     c@s,eZdZdZdeeejddddZe e fe ee e e ee fddd Ze ee e ed d d Ze e e ee ed ddZee eeeefdddZee ee e edddZee ee e edddZejeeefe e edddZee ee e edddZdS)ra Helper tool to embed Infinity. It is not a part of Langchain's stable API, direct use discouraged. Example: .. code-block:: python mini_client = TinyAsyncInfinityEmbeddingClient( ) embeds = mini_client.embed( model="BAAI/bge-small", text=["doc1", "doc2"] ) # or embeds = await mini_client.aembed( model="BAAI/bge-small", text=["doc1", "doc2"] ) http://localhost:7797/v1N)r aiosessionrcCs6||_||_|jdus$t|jdkr,tdd|_dS)Nz( param `host` must be set to a valid url)rr3len ValueError _batch_size)r"rr3rrr__init__s z/TinyAsyncOpenAIInfinityEmbeddingClient.__init__)rsorterrcsRtdkrddfStfddDfddD}|fddfS)aSort texts in ascending order, and delivers a lambda expr, which can sort a same length list https://github.com/UKPLab/sentence-transformers/blob/ c5f93f70eca933c78695c5bc686ceda59651ae3b/sentence_transformers/SentenceTransformer.py#L156 Args: texts (List[str]): _description_ sorter (Callable, optional): _description_. Defaults to len. Returns: Tuple[List[str], Callable]: _description_ Example: ``` texts = ["one","three","four"] perm_texts, undo = self._permute(texts) texts == undo(perm_texts) ``` cSs|S)Nr)trrrzATinyAsyncOpenAIInfinityEmbeddingClient._permute..csg|]}| qSrr).0Zsen)r:rr r>zCTinyAsyncOpenAIInfinityEmbeddingClient._permute..csg|] }|qSrrr?idx)rrrr@r>csfddtDS)Ncsg|] }|qSrrrAZunsorted_embeddingsrrr@szUTinyAsyncOpenAIInfinityEmbeddingClient._permute....)npargsortrC)length_sorted_idxrCrr=s )r6rDrE)rr:Z texts_sortedr)rFr:rr_permutes   z/TinyAsyncOpenAIInfinityEmbeddingClient._permutercCsJt|dkr|gSg}tdt||jD]}|||||jq(|S)aX splits Lists of text parts into batches of size max `self._batch_size` When encoding vector database, Args: texts (List[str]): List of sentences self._batch_size (int, optional): max batch size of one request. Returns: List[List[str]]: Batches of List of sentences r;r)r6ranger8append)r"rZbatches start_indexrrr_batchs z-TinyAsyncOpenAIInfinityEmbeddingClient._batch)batch_of_textsrcCs@t|dkr$t|ddkr$|dSg}|D]}||q,|S)Nr;r)r6extend)rLrZsublistrrr_unbatchs  z/TinyAsyncOpenAIInfinityEmbeddingClient._unbatch)rrrcCs"t|jdddit||ddS)zBuild the kwargs for the Post request, used by sync Args: model (str): _description_ texts (List[str]): _description_ Returns: Dict[str, Collection[str]]: _description_ z /embeddingsz content-typezapplication/json)inputr)urlheadersjson)dictr)r"rrrrr_kwargs_post_requests  z;TinyAsyncOpenAIInfinityEmbeddingClient._kwargs_post_request)r batch_textsrcCsRtjfi|j||d}|jdkrzNTinyAsyncOpenAIInfinityEmbeddingClient._sync_request_embed..data)requestspostrT status_code Exceptionr'rR)r"rrUresponserrr_sync_request_embeds  z:TinyAsyncOpenAIInfinityEmbeddingClient._sync_request_embedc Cs||\}}||}|j|gt||f}t|dkrHtt|}n6td}t|j|}Wdn1st0Y||} || } | S)zcall the embedding of model Args: model (str): to embedding model texts (List[str]): List of sentences to embed. Returns: List[List[float]]: List of vectors for each sentence r; N)rGrKrcr6listmaprrN) r"rr perm_textsunpermute_funcperm_texts_batchedZmap_argsembeddings_batch_permpembeddings_permr#rrrr s     , z,TinyAsyncOpenAIInfinityEmbeddingClient.embed)sessionkwargsrc s|jfi|4IdHX}|jdkrzITinyAsyncOpenAIInfinityEmbeddingClient._async_request..)r_statusrar'rR)r"rmrnrbrZrrr_async_requests z5TinyAsyncOpenAIInfinityEmbeddingClient._async_requestc s|\}}|}tjdtjddd4IdH8tjfdd|DIdH}WdIdHq1IdHsz0Y|}||}|S)zcall the embedding of model, async method Args: model (str): to embedding model texts (List[str]): List of sentences to embed. Returns: List[List[float]]: List of vectors for each sentence Trd)limit) trust_envZ connectorNcs$g|]}jj|ddqS)r)rmrn)rprT)r?r<rr"rmrrr@9s  zATinyAsyncOpenAIInfinityEmbeddingClient.aembed..)rGrKaiohttp ClientSessionZ TCPConnectorasynciogatherrN) r"rrrgrhrirjrlr#rrsrr%'s   4 z-TinyAsyncOpenAIInfinityEmbeddingClient.aembed)r2N)r*r+r,r-r.rrtrur9 staticmethodr6rrrrGrKrrNrrTr1rcr rpr%rrrrrws4 !   r)r-rvconcurrent.futuresrtypingrrrrrrrtnumpyrDr^Zlangchain_core.embeddingsr Zlangchain_core.utilsr Zpydanticr r r __all__rrrrrrs    f