Update app.py

app.py

@@ -1,10 +1,11 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-
+from langchain_community.chat_models import ChatOllama
+from langchain_core.prompts import ChatPromptTemplate
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 
 def respond(
@@ -14,16 +15,30 @@ def respond(
     max_tokens,
     temperature,
     top_p,
+    model_name="llama3-8b",
+    api_key=None
 ):
-    messages = [{"role": "system", "content": system_message}]
+    client = ChatOllama(
+        model=model_name,
+        base_url="https://lintasmediadanawa-hf-llm-api.hf.space", 
+        headers={"Authorization": f"Bearer {api_key}"},
+        temperature=temperature,
+        top_p=top_p,
+        max_tokens=max_tokens
+    )
+    
+    messages = [("system", system_message)]
 
     for val in history:
         if val[0]:
-            messages.append({"role": "user", "content": val[0]})
+            # messages.append({"role": "user", "content": val[0]})
+            messages.append(("human", val[0]))
         if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+            # messages.append({"role": "assistant", "content": val[1]})
+            messages.append(("ai", val[1]))
 
-    messages.append({"role": "user", "content": message})
+    # messages.append({"role": "user", "content": message})
+    messages.append(("user", message))
 
     response = ""
 
@@ -55,6 +70,8 @@ demo = gr.ChatInterface(
             step=0.05,
             label="Top-p (nucleus sampling)",
         ),
+        gr.Textbox(value="llama3-8b", label="Available Model Name, please refer to https://lintasmediadanawa-hf-llm-api.hf.space/api/tags")
+        gr.Textbox(value="hf_xxx", label="Huggingface API key")
     ],
 )