initial commit

app.py

@@ -10,7 +10,7 @@ import time
 
 API_URL = "https://api-inference.huggingface.co/models/HuggingFaceH4/zephyr-7b-beta"
 headers = {"Authorization": f"Bearer {os.environ.get('API_KEY')}"}
-# retrieval = Client("https://ishaan-mital-ncert-helper-vector-db.hf.space/--replicas/149bl5mjn/")
+retrieval = Client("https://ishaan-mital-ncert-helper-vector-db.hf.space/--replicas/149bl5mjn/")
 
 embed_model_id = 'sentence-transformers/all-MiniLM-L6-v2'
 # device = f'cuda:{cuda.current_device()}' if cuda.is_available() else 'cpu'
@@ -63,7 +63,7 @@ rag_pipeline = RetrievalQA.from_chain_type(
 
 
 def main(question):
-    return rag_pipeline(question)
+    # return rag_pipeline(question)
     # global chatbot
     # context = retrieval.predict(question, api_name = "/predict")
     # answer=call_llm_api(question,context)