Used New Serverless Inference Calls

app.py

@@ -9,7 +9,7 @@ import gradio as gr
 CHROMA_PATH = "chroma"
 
 # Hugging Face API setup
-repo_id = "Qwen/Qwen2.5-Coder-32B-Instruct"
+repo_id = "mistralai/Mistral-7B-Instruct-v0.3"
 
 PROMPT_TEMPLATE = """
 Answer the question based on the context provided. If no relevant information is found, state so.
@@ -40,13 +40,23 @@ class LocalEmbeddingFunction:
 
 
 class LLM:
-    llm = HuggingFaceEndpoint(
-        repo_id=repo_id,
-        temperature=0.2,
+    client = InferenceClient(
+        provider="hyperbolic",
     )
 
     def generate_response(self, prompt):
-        return self.llm.invoke(prompt)
+        completion = client.chat.completions.create(
+            model=repo_id,
+            messages=[
+                {
+                    "role": "user",
+                    "content": prompt
+                }
+            ],
+            max_tokens=250,
+            temperature=0.2
+        )
+        return str(completion.choices[0].message.content)
 
 
 def get_embedding_function():