Update app.py

app.py

@@ -22,10 +22,6 @@ collection = client.get_or_create_collection("patents")
 
 collection.add(documents=docs,ids=ids)
 
-def text_embedding(text)-> None:
-    model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
-    return model.encode(text)
-
 def gen_context(query):
     vector = text_embedding(query).tolist()
     
@@ -37,13 +33,8 @@ def gen_context(query):
 
 def chat_completion(user_prompt):
     length = 1000
-    system_prompt = """\
-You are a helpful AI assistant that can answer questions on the patents dataset. Answer based on the context provided.If you cannot find the correct answer, say I don't know. Be concise and just include the response"""
-    final_prompt = f"""<s>[INST]<<SYS>>
-    {system_prompt}
-    <</SYS>>
-    
-    {user_prompt}[/INST]"""
+    system_prompt = """\You are a helpful AI assistant that can answer questions on the patents dataset. Answer based on the context provided.If you cannot find the correct answer, say I don't know. Be concise and just include the response"""
+    final_prompt = f"""<s>[INST]<<SYS>>{system_prompt}<</SYS>>{user_prompt}[/INST]"""
     
     return client.text_generation(prompt=final_prompt,max_new_tokens = length).strip()
 
@@ -51,28 +42,7 @@ You are a helpful AI assistant that can answer questions on the patents dataset.
 
 client = InferenceClient(model = "mistralai/Mixtral-8x7B-Instruct-v0.1")
 
-def chat_completion(query):
-    length = 1000
-    
-    context = gen_context(query)
-    
-    user_prompt = f"""
-Based on the context:
-{context}
-Answer the below query:
-{query}
-"""
-    system_prompt = """\
-You are a helpful AI assistant that can answer questions on the patents dataset. Answer based on the context provided.If you cannot find the correct answer, say I don't know. Be concise and just include the response"""
-    final_prompt = f"""<s>[INST]<<SYS>>
-    {system_prompt}
-    <</SYS>>
-    
-    {user_prompt}[/INST]"""
-    
-    
-    
-    return client.text_generation(prompt=final_prompt,max_new_tokens = length).strip()
+
 
 demo = gr.Interface(fn=chat_completion, 
                     inputs=[gr.Textbox(label="Query", lines=2)],