Update appStore/rag.py

appStore/rag.py

@@ -193,21 +193,23 @@ def run_query(context, label):
     '''
     chatbot_role = """You are an analyst specializing in climate change impact assessments and producing insights from policy documents."""
 
+    messages = [{"role": "system", "content": chatbot_role},{"role": "user", "content": get_prompt(context, label)}]
+    
     # res = openai.ChatCompletion.create(model=model_select, messages=[{"role": "user", "content": get_prompt(docs)}])
     # result = res.choices[0].message.content
 
     # Initialize the client, pointing it to one of the available models
-    client = InferenceClient()
-
-    response = client.chat.completions.create(
-        model="meta-llama/Meta-Llama-3.1-8B-Instruct",
-        messages=[
-          ChatMessage(role="system", content=chatbot_role),
-          ChatMessage(role="user", content=get_prompt(context, label)),
-        ],
-        stream=True,
-        max_tokens=500
-    )
+    client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct", token = hf_token)
+
+    # response = client.chat.completions.create(
+    #     model="meta-llama/Meta-Llama-3.1-8B-Instruct",
+    #     messages=[
+    #       ChatMessage(role="system", content=chatbot_role),
+    #       ChatMessage(role="user", content=get_prompt(context, label)),
+    #     ],
+    #     stream=True,
+    #     max_tokens=500
+    # )
 
     # iterate and print stream
     # for message in chat_completion: