Spaces:
Running
Running
File size: 1,278 Bytes
2217335 858a66e 033e5a9 2217335 b10c5fb 2217335 858a66e 2217335 708527c 2217335 858a66e 2217335 c774338 1983ef1 c774338 843fee2 084159d 929fe0b 1983ef1 c774338 858a66e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 |
import logging
import os
import requests
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import HuggingFaceEmbeddings
class VectorStore:
vectorstore = "index-BAAI_bge-m3-1500-200-recursive_splitter-CA_ES_UE"
def __init__(self, embeddings_model):
# load vectore store
embeddings = HuggingFaceEmbeddings(model_name=embeddings_model, model_kwargs={'device': 'cpu'})
self.vectore_store = FAISS.load_local(self.vectorstore, embeddings, allow_dangerous_deserialization=True)
logging.info("RAG loaded!")
def get_context(self, instruction, number_of_contexts=2):
documentos = self.vectore_store.similarity_search_with_score(instruction, k=number_of_contexts)
return self.beautiful_context(documentos)
def beautiful_context(self, docs):
text_context = ""
full_context = ""
source_context = []
for doc in docs:
text_context += doc[0].page_content
full_context += doc[0].metadata["Títol de la norma"] + "\n\n"
full_context += doc[0].metadata["url"] + "\n\n"
full_context += doc[0].page_content + "\n"
source_context.append(doc[0].metadata["url"])
return full_context
|