Update chatbot_backend.py

chatbot_backend.py

@@ -1,41 +1,49 @@
 import os
-from langchain_community.llms import Ollama
-from langchain_community.embeddings import OllamaEmbeddings
+import asyncio
 from langchain_community.document_loaders import TextLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.vectorstores import FAISS
-from langchain.memory import ConversationBufferMemory
+from langchain.text_splitter import CharacterTextSplitter
+from langchain_google_genai import ChatGoogleGenerativeAI, GoogleGenerativeAIEmbeddings
+from langchain.vectorstores import FAISS
 from langchain.chains import ConversationalRetrievalChain
 
-# ✅ Memory
-memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+google_api_key = os.getenv("GOOGLE_API_KEY")
 
-# ✅ LLM (Ollama model, e.g. llama3, mistral, phi3)
-llm = Ollama(model="llama3")
+# 🟢 Event loop safe embeddings initializer
+def get_embeddings():
+    try:
+        asyncio.get_running_loop()
+    except RuntimeError:
+        loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(loop)
+
+    return GoogleGenerativeAIEmbeddings(
+        model="models/embedding-001",
+        google_api_key=google_api_key
+    )
 
-# ✅ Load + Split Docs
-loader = TextLoader("data.txt", encoding="utf-8")
+# 🟢 Use loader safely
+loader = TextLoader("data.txt")
 docs = loader.load()
-splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
-chunks = splitter.split_documents(docs)
-
-# ✅ Embeddings + VectorStore
-embeddings = OllamaEmbeddings(model="llama3")
-vectorstore = FAISS.from_documents(documents=chunks, embedding=embeddings)
-retriever = vectorstore.as_retriever(search_kwargs={"k": 2})
-
-# ✅ Conversational Retrieval Chain (with memory)
-conversational_chain = ConversationalRetrievalChain.from_llm(
-    llm=llm,
-    retriever=retriever,
-    memory=memory,
-    return_source_documents=False
+
+# 🟢 Split text into chunks
+text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+documents = text_splitter.split_documents(docs)
+
+# 🟢 Create vectorstore with embeddings
+embeddings = get_embeddings()
+db = FAISS.from_documents(documents, embeddings)
+
+# 🟢 Conversational chain
+qa = ConversationalRetrievalChain.from_llm(
+    ChatGoogleGenerativeAI(model="gemini-2.5-flash", google_api_key=google_api_key),
+    db.as_retriever()
 )
 
-# ✅ Ask bot function
-def ask_bot(query: str) -> str:
-    try:
-        response = conversational_chain.invoke({"question": query})
-        return response["answer"]
-    except Exception as e:
-        return f"Error: {str(e)}"
+# 🟢 Function to interact with bot
+chat_history = []
+
+def ask_bot(query: str):
+    global chat_history
+    result = qa({"question": query, "chat_history": chat_history})
+    chat_history.append((query, result["answer"]))
+    return result["answer"]