tj ddlmZmZmZddlmZddlmZddlm Z dedededeee fd Z Gd d e eZ d S) )AnyCallableList) Embeddings) ConfigDict)SelfHostedPipelinepipelineargskwargsreturnc||i|S)zInference function to send to the remote hardware. Accepts a sentence_transformer model_id and returns a list of embeddings for each document in the batch. )r r r s h/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/langchain_community/embeddings/self_hosted.py_embed_documentsr s 8T $V $ $$ceZdZUdZeZeed< dZe ed< e dZ de e de e efd Zd e de efd ZdS) SelfHostedEmbeddingsaCustom embedding models on self-hosted remote hardware. Supported hardware includes auto-launched instances on AWS, GCP, Azure, and Lambda, as well as servers specified by IP address and SSH credentials (such as on-prem, or another cloud like Paperspace, Coreweave, etc.). To use, you should have the ``runhouse`` python package installed. Example using a model load function: .. code-block:: python from langchain_community.embeddings import SelfHostedEmbeddings from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline import runhouse as rh gpu = rh.cluster(name="rh-a10x", instance_type="A100:1") def get_pipeline(): model_id = "facebook/bart-large" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) return pipeline("feature-extraction", model=model, tokenizer=tokenizer) embeddings = SelfHostedEmbeddings( model_load_fn=get_pipeline, hardware=gpu model_reqs=["./", "torch", "transformers"], ) Example passing in a pipeline path: .. code-block:: python from langchain_community.embeddings import SelfHostedHFEmbeddings import runhouse as rh from transformers import pipeline gpu = rh.cluster(name="rh-a10x", instance_type="A100:1") pipeline = pipeline(model="bert-base-uncased", task="feature-extraction") rh.blob(pickle.dumps(pipeline), path="models/pipeline.pkl").save().to(gpu, path="models") embeddings = SelfHostedHFEmbeddings.from_pipeline( pipeline="models/pipeline.pkl", hardware=gpu, model_reqs=["./", "torch", "transformers"], ) inference_fnNinference_kwargsforbid)extratextsr cttd|}||j|}t |ts|S|S)zCompute doc embeddings using a HuggingFace transformer model. Args: texts: The list of texts to embed.s Returns: List of embeddings, one for each text. c.|ddS)N  )replace)xs rz6SelfHostedEmbeddings.embed_documents..Rs199T3#7#7r)listmapclient pipeline_ref isinstancetolist)selfr embeddingss rembed_documentsz$SelfHostedEmbeddings.embed_documentsIs_S77??@@[[!2E:: *d++ '$$&& &rtextc|dd}||j|}t|ts|S|S)zCompute query embeddings using a HuggingFace transformer model. Args: text: The text to embed. Returns: Embeddings for the text. rr)rr"r#r$r r%)r&r)r's r embed_queryz SelfHostedEmbeddings.embed_queryXsW||D#&&[[!2D99 *d++ '$$&& &r)__name__ __module__ __qualname____doc__rrr__annotations__rrr model_configrstrfloatr(r+rrrrrs++Z.L(---N c   ?:L T#Y 4U 3D      U      rrN) typingrrrlangchain_core.embeddingsrpydanticr$langchain_community.llms.self_hostedrr3rrrrrr8s&&&&&&&&&&000000CCCCCC%s%3%#%$tE{BS%%%%SSSSS-zSSSSSr