fix linting

Author: edkaya

genai/controller/generate_controller.py

@@ -80,7 +80,7 @@ def upload_file():
 def generate():
     """API Endpoint for generating recipe response based on document retrieval
 
-    This endpoint processes user queries against a vector database of recipes 
+    This endpoint processes user queries against a vector database of recipes
     and returns AI-generated responses using retrieved context.
 
     Request Body:

genai/rag/llm/chat_model.py

@@ -11,7 +11,7 @@ class ChatModel(BaseChatModel):
     model_name: str = Field(default="llama3.3:latest")
 
     def _generate(self, messages: List[BaseMessage],
-                  stop=None, 
+                  stop=None,
                   **kwargs) -> ChatResult:
         prompt = "\n".join([
             msg.content for msg in messages if isinstance(msg, HumanMessage)
@@ -31,18 +31,21 @@ def _llm_type(self) -> str:
     def get_system_prompt(self) -> str:
         """System prompt for the LLM"""
         return """
-            You are RecipAI, an intelligent assistant that helps users discover and generate 
-            recipes based on the ingredients they provide. 
-            
-            Use the contextual information provided below to tailor your responses. 
-            
-            If relevant recipes or suggestions are found in the context, prioritize 
-            those. If no relevant context is available, use your own knowledge to help the user.
+            You are an intelligent assistant that helps users discover
+            and generate recipes based on the ingredients they provide.
+
+            Use the contextual information provided below to tailor
+            your responses.
+
+            If relevant recipes or suggestions are found in the context,
+            prioritize those. If no relevant context is available,
+            use your own knowledge to help the user.
 
             Context:
             {context}
 
-            Be clear, creative, and helpful. If the user also asks follow-up 
-            questions (e.g., dietary adjustments, name references, meal timing), 
-            answer them precisely based on the context and query.
+            Be clear, creative, and helpful. If the user also asks
+            follow-up questions (e.g., dietary adjustments, name references,
+            meal timing), answer them precisely based on the
+            context and query.
             """

genai/service/rag_service.py

@@ -3,7 +3,7 @@
 from langchain_qdrant import QdrantVectorStore
 from langchain_core.messages import BaseMessage, HumanMessage
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
-from genai.rag.llm.chat_model import ChatModel
+# from genai.rag.llm.chat_model import ChatModel
 
 
 def retrieve_similar_docs(vector_store: QdrantVectorStore, user_query: str):
@@ -37,6 +37,9 @@ def prepare_prompt(system_prompt: str,
 # if __name__ == "__main__":
 #     msg = HumanMessage(content="My name is John Doe.")
 #     llm = ChatModel()
-#     prompt = prepare_prompt(llm.get_system_prompt(), "Suggest me a basic breakfast. Btw, what is my name?", "", [msg])
+#     prompt = prepare_prompt(llm.get_system_prompt(), 
+#                             "Suggest me a basic breakfast. Btw, what is my name?",
+#                             "", 
+#                             [msg])
 #     response = llm.invoke(prompt)
-#     print(response.content)
+#     print(response.content)