Update chatbot_rag.py

chatbot_rag.py

@@ -12,23 +12,22 @@ from langchain_chroma import Chroma
 def build_qa():
     """Builds and returns the RAG QA pipeline."""
 
-    # 1. Embeddings
+    # 1. Load embeddings + DB
     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-
     vectorstore = Chroma(
-    persist_directory="db",
-    collection_name="rag-docs",
-    embedding_function=embeddings,
+        persist_directory="db",
+        collection_name="rag-docs",
+        embedding_function=embeddings,
     )
 
-    # 3. LLM
-    model_id = "microsoft/phi-2"
+    # 2. LLM (instruction-tuned preferred)
+    model_id = "microsoft/phi-3-mini-4k-instruct"
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     model = AutoModelForCausalLM.from_pretrained(model_id)
     pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512)
     llm = HuggingFacePipeline(pipeline=pipe)
 
-    # 4. QA Chain
+    # 3. QA Chain
     retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
     qa = RetrievalQA.from_chain_type(llm=llm, retriever=retriever, return_source_documents=False)