Fix all deprecated langchain imports to use new module structure

medrax/rag/rag.py

@@ -9,10 +9,11 @@ from langchain_community.document_loaders import TextLoader, PyPDFLoader, Docx2t
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_pinecone import PineconeVectorStore
 from pinecone import Pinecone
-from langchain.chains import RetrievalQA
-from langchain.memory import ConversationBufferMemory
-from langchain.schema import BaseRetriever
-from langchain.docstore.document import Document
+from langchain.chains.retrieval_qa.base import RetrievalQA
+from langchain_community.chat_message_histories import ChatMessageHistory
+from langchain_core.runnables.history import RunnableWithMessageHistory
+from langchain_core.retrievers import BaseRetriever
+from langchain_core.documents import Document
 from typing import Callable
 from datasets import load_dataset
 from tqdm import tqdm

medrax/tools/rag.py

@@ -1,6 +1,6 @@
-from langchain.tools import BaseTool
+from langchain_core.tools import BaseTool
 from medrax.rag.rag import RAGConfig, CohereRAG
-from langchain.chains import RetrievalQA
+from langchain.chains.retrieval_qa.base import RetrievalQA
 from typing import Dict, Tuple, Any
 
 

scripts/pdf_to_hf_dataset.py

@@ -22,7 +22,7 @@ import hashlib
 import re
 from langchain_community.document_loaders import PyPDFLoader
 from langchain_text_splitters import RecursiveCharacterTextSplitter
-from langchain.docstore.document import Document
+from langchain_core.documents import Document
 import pandas as pd
 from datasets import Dataset