Update app.py

app.py

@@ -8,52 +8,86 @@ HF_TOKEN = os.getenv("HF_TOKEN")  # Replace with your actual token if not using
 # Initialize the Gradio Client for the specified API
 client = Client("on1onmangoes/CNIHUB10724v9", hf_token=HF_TOKEN)
 
-# OG code in V9
+# Function to handle chat API call
 def stream_chat_with_rag(
     message: str,
     history: list,
     client_name: str,
     system_prompt: str,
-    num_retrieved_docs: int = 10,
-    num_docs_final: int = 9,
-    temperature: float = 0, 
-    max_new_tokens: int = 1024, 
-    top_p: float = 1.0, 
-    top_k: int = 20, 
-    penalty: float = 1.2,
+    num_retrieved_docs: int,
+    num_docs_final: int,
+    temperature: float,
+    max_new_tokens: int,
+    top_p: float,
+    top_k: int,
+    penalty: float,
 ):
+    # Use the parameters provided by the UI
+    response = client.predict(
+        message=message,
+        client_name=client_name,
+        system_prompt=system_prompt,
+        num_retrieved_docs=num_retrieved_docs,
+        num_docs_final=num_docs_final,
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        top_k=top_k,
+        penalty=penalty,
+        api_name="/chat"
+    )
+    # Return the assistant's reply
+    return response
 
-# Function to handle chat API call
-# def stream_chat_with_rag(message, system_prompt, num_retrieved_docs, num_docs_final, temperature, max_new_tokens, top_p, top_k, penalty):
-#     response = client.predict(
-#         message=message,
-#         client_name="rosariarossi",  # Hardcoded client name
-#         system_prompt=system_prompt,
-#         num_retrieved_docs=num_retrieved_docs,
-#         num_docs_final=num_docs_final,
-#         temperature=temperature,
-#         max_new_tokens=max_new_tokens,
-#         top_p=top_p,
-#         top_k=top_k,
-#         penalty=penalty,
-#         api_name="/chat"
-#     )
-#     return response
 
-    result = client.predict(
-            message=message,
-            client_name="rosariarossi",
-            system_prompt="You are an expert assistant",
-            num_retrieved_docs=10,
-            num_docs_final=9,
-            temperature=0,
-            max_new_tokens=1024,
-            top_p=1,
-            top_k=20,
-            penalty=1.2,
-            api_name="/chat"
-    )
-    return result
+
+
+# # OG code in V9
+# def stream_chat_with_rag(
+#     message: str,
+#     history: list,
+#     client_name: str,
+#     system_prompt: str,
+#     num_retrieved_docs: int = 10,
+#     num_docs_final: int = 9,
+#     temperature: float = 0, 
+#     max_new_tokens: int = 1024, 
+#     top_p: float = 1.0, 
+#     top_k: int = 20, 
+#     penalty: float = 1.2,
+# ):
+
+# # Function to handle chat API call
+# # def stream_chat_with_rag(message, system_prompt, num_retrieved_docs, num_docs_final, temperature, max_new_tokens, top_p, top_k, penalty):
+# #     response = client.predict(
+# #         message=message,
+# #         client_name="rosariarossi",  # Hardcoded client name
+# #         system_prompt=system_prompt,
+# #         num_retrieved_docs=num_retrieved_docs,
+# #         num_docs_final=num_docs_final,
+# #         temperature=temperature,
+# #         max_new_tokens=max_new_tokens,
+# #         top_p=top_p,
+# #         top_k=top_k,
+# #         penalty=penalty,
+# #         api_name="/chat"
+# #     )
+# #     return response
+
+#     result = client.predict(
+#             message=message,
+#             client_name="rosariarossi",
+#             system_prompt="You are an expert assistant",
+#             num_retrieved_docs=10,
+#             num_docs_final=9,
+#             temperature=0,
+#             max_new_tokens=1024,
+#             top_p=1,
+#             top_k=20,
+#             penalty=1.2,
+#             api_name="/chat"
+#     )
+#     return result