File size: 563 Bytes
2d176ee
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
from langchain.vectorstores import FAISS
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter

def build_vector_store(doc_path="model_docs/tsnet_manual.txt"):
    loader = TextLoader(doc_path)
    docs = loader.load()
    splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
    chunks = splitter.split_documents(docs)
    embedding = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
    return FAISS.from_documents(chunks, embedding)