File size: 2,060 Bytes
8f4d57a |
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 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
import tiktoken
from langchain_text_splitters import CharacterTextSplitter
from langchain_chroma import Chroma
from langchain_community.embeddings import HuggingFaceBgeEmbeddings
from langchain.document_loaders import PyMuPDFLoader,Docx2txtLoader
from transformers import pipeline
from app_config import VECTOR_MAX_TOKENS, VECTORS_TOKEN_OVERLAP_SIZE
from langchain.docstore.document import Document
from dotenv import load_dotenv
from pathlib import Path
import os
env_path = Path('.') / '.env'
load_dotenv(dotenv_path=env_path)
tokenizer = tiktoken.get_encoding('cl100k_base')
# create the length function
def tiktoken_len(text):
tokens = tokenizer.encode(
text,
disallowed_special=()
)
return len(tokens)
def get_vectorstore_with_doc_from_pdf(pdf_path):
model_name = "BAAI/bge-small-en"
model_kwargs = {"device": "cpu"}
encode_kwargs = {"normalize_embeddings": True}
hf = HuggingFaceBgeEmbeddings(
model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs
)
loader = PyMuPDFLoader(pdf_path)
documents = loader.load()
print(len(documents))
all_splits = [doc.page_content for doc in documents]
vectorstore = Chroma.from_texts(texts=all_splits, embedding=hf)
return vectorstore
def get_vectorstore_with_doc_from_word(word_path):
model_name = "BAAI/bge-small-en"
model_kwargs = {"device": "cpu"}
encode_kwargs = {"normalize_embeddings": True}
hf = HuggingFaceBgeEmbeddings(
model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs
)
loader = Docx2txtLoader(word_path)
documents = loader.load()
text_splitter = CharacterTextSplitter(
separator="Page :",
)
# all_splits = text_splitter.split_text(data)
print(len(documents))
print("all splits ........................")
all_splits = text_splitter.split_text(documents[0].page_content)
print(len(all_splits))
vectorstore = Chroma.from_texts(texts=all_splits, embedding=hf)
return vectorstore
|