rag: updated deprecated imports and calls

src/rag.py

@@ -1,14 +1,14 @@
 
 import dotenv
 import os
-from langchain.document_loaders import UnstructuredURLLoader, PyPDFLoader
+from langchain_community.document_loaders import UnstructuredURLLoader, PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 
-# from langchain.embeddings import OpenAIEmbeddings
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain.vectorstores import Chroma
-from langchain.chat_models import ChatOpenAI
-from langchain.llms import HuggingFaceHub
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain_openai import ChatOpenAI
+# from langchain_community.llms import HuggingFaceHub
+from langchain_huggingface import HuggingFaceEndpoint
 from langchain.chains import RetrievalQA
 from langchain.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate
 from tqdm import tqdm
@@ -85,9 +85,10 @@ class RAG():
                 temperature=0)
         elif self.use_model ==  'zephyr-7b-alpha':
             print(f'As llm, using HF model: {self.use_model}')
-            llm = HuggingFaceHub(
-                repo_id="huggingfaceh4/zephyr-7b-alpha", 
-                model_kwargs={"temperature": 0.5, "max_length": 64,"max_new_tokens":512}
+            llm = HuggingFaceEndpoint(
+                repo_id=f"huggingfaceh4/{self.use_model}",
+                temperature=0.1,
+                max_new_tokens=512
                 )
         return llm
 
@@ -133,7 +134,7 @@ class RAG():
         )
 
     def ask_QAbot(self, question):
-        result = self.QAbot({"query": question})
+        result = self.QAbot.invoke({"query": question})
         sources = [doc.metadata.get('source', 'Unknown source') for doc in result["source_documents"]]
         response = {
             "question": question,