Update src/rag_utils.py
Browse files- src/rag_utils.py +6 -0
src/rag_utils.py
CHANGED
|
@@ -1,11 +1,17 @@
|
|
|
|
|
| 1 |
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
| 2 |
from langchain_community.document_loaders import PyPDFLoader
|
| 3 |
from langchain_chroma import Chroma
|
| 4 |
from langchain_huggingface import HuggingFaceEmbeddings
|
| 5 |
|
| 6 |
|
|
|
|
|
|
|
|
|
|
| 7 |
embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
|
| 8 |
|
|
|
|
|
|
|
| 9 |
def load_pdf_document(file_path):
|
| 10 |
document_loader = PyPDFLoader(file_path)
|
| 11 |
return document_loader.load()
|
|
|
|
| 1 |
+
import os
|
| 2 |
from langchain_text_splitters import RecursiveCharacterTextSplitter
|
| 3 |
from langchain_community.document_loaders import PyPDFLoader
|
| 4 |
from langchain_chroma import Chroma
|
| 5 |
from langchain_huggingface import HuggingFaceEmbeddings
|
| 6 |
|
| 7 |
|
| 8 |
+
os.environ["TRANSFORMERS_CACHE"] = "/tmp/hf_cache"
|
| 9 |
+
os.environ["HF_HOME"] = "/tmp/hf_cache"
|
| 10 |
+
|
| 11 |
embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
|
| 12 |
|
| 13 |
+
|
| 14 |
+
|
| 15 |
def load_pdf_document(file_path):
|
| 16 |
document_loader = PyPDFLoader(file_path)
|
| 17 |
return document_loader.load()
|