Update app.py

app.py

@@ -9,18 +9,10 @@ from duckduckgo_search import DDGS
 
 # Environment variables and configurations
 huggingface_token = os.environ.get("HUGGINGFACE_TOKEN")
-llama_cloud_api_key = os.environ.get("LLAMA_CLOUD_API_KEY")
-ACCOUNT_ID = os.environ.get("CLOUDFARE_ACCOUNT_ID")
-API_TOKEN = os.environ.get("CLOUDFLARE_AUTH_TOKEN")
-API_BASE_URL = f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/"
-
-print(f"ACCOUNT_ID: {ACCOUNT_ID}")
-print(f"CLOUDFLARE_AUTH_TOKEN: {API_TOKEN[:5]}..." if API_TOKEN else "Not set")
 
 MODELS = [
     "mistralai/Mistral-7B-Instruct-v0.3",
     "mistralai/Mixtral-8x7B-Instruct-v0.1",
-    "@cf/meta/llama-3.1-8b-instruct",
     "mistralai/Mistral-Nemo-Instruct-2407"
 ]
 
@@ -56,25 +48,20 @@ def get_response_with_search(query, model, num_calls=3, temperature=0.2):
 Write a detailed and complete research document that fulfills the following user request: '{query}'
 After writing the document, please provide a list of sources used in your response."""
 
-    if model == "@cf/meta/llama-3.1-8b-instruct":
-        # Use Cloudflare API
-        for response in get_response_from_cloudflare(prompt="", context=context, query=query, num_calls=num_calls, temperature=temperature, search_type="web"):
-            yield response, ""
-    else:
-        # Use Hugging Face API
-        client = InferenceClient(model, token=huggingface_token)
-        main_content = ""
-        for i in range(num_calls):
-            for message in client.chat_completion(
-                messages=[{"role": "user", "content": prompt}],
-                max_tokens=10000,
-                temperature=temperature,
-                stream=True,
-            ):
-                if message.choices and message.choices[0].delta and message.choices[0].delta.content:
-                    chunk = message.choices[0].delta.content
-                    main_content += chunk
-                    yield main_content, ""
+    # Use Hugging Face API
+    client = InferenceClient(model, token=huggingface_token)
+    main_content = ""
+    for i in range(num_calls):
+        for message in client.chat_completion(
+            messages=[{"role": "user", "content": prompt}],
+            max_tokens=10000,
+            temperature=temperature,
+            stream=True,
+        ):
+            if message.choices and message.choices[0].delta and message.choices[0].delta.content:
+                chunk = message.choices[0].delta.content
+                main_content += chunk
+                yield main_content, ""
 
 def respond(message, history, model, temperature, num_calls):
     logging.info(f"User Query: {message}")
@@ -101,6 +88,7 @@ css = """
     width: 100%;
 }
 """
+
 # Gradio interface setup
 def create_gradio_interface():
     custom_placeholder = "Enter your question here for web search."
@@ -108,7 +96,7 @@ def create_gradio_interface():
     demo = gr.ChatInterface(
         respond,
         additional_inputs=[
-            gr.Dropdown(choices=MODELS, label="Select Model", value=MODELS[3]),
+            gr.Dropdown(choices=MODELS, label="Select Model", value=MODELS[2]),
             gr.Slider(minimum=0.1, maximum=1.0, value=0.2, step=0.1, label="Temperature"),
             gr.Slider(minimum=1, maximum=5, value=1, step=1, label="Number of API Calls"),
         ],