Update app.py

app.py

@@ -304,7 +304,7 @@ def format_kadi_apy_library_context(docs):
         type_info = doc.metadata.get("type", "Unknown Type")
         source_info = doc.metadata.get("source", "Unknown Type")
         # Format metadata and document content
-        print("YYYYYYYEEEEEEEEEEEEEEE222222222222222222222222222222:}\n\n", doc.page_content)
+        #print("YYYYYYYEEEEEEEEEEEEEEE222222222222222222222222222222:}\n\n", doc.page_content)
         formatted_doc = f"# source: {source_info}\n# class: {class_info}\n# type: {type_info}\n{doc.page_content}\n\n\n"
         doc_context.append(formatted_doc)
     
@@ -316,7 +316,7 @@ def format_kadi_api_doc_context(docs):
 
     for doc in docs:
         source_info = doc.metadata.get("source", "Unknown Type")
-        print("YYYYYYYEEEEEEEEEEEEEEE:}\n\n", doc.page_content)
+        #print("YYYYYYYEEEEEEEEEEEEEEE:}\n\n", doc.page_content)
         formatted_doc = f"# source: {source_info}\n{doc.page_content}\n\n\n"
         doc_context.append(formatted_doc)
     
@@ -326,10 +326,36 @@ def format_kadi_api_doc_context(docs):
                    
 def rag_workflow(query):
     
-  #  retrieved_doc_chunks = retrieve_from_vectorstore (docstore, query, k=5)
-  #  retrieved_code_chunks = retrieve_from_vectorstore(codestore, query, k=5)
-
+   rewrite_prompt = f"""You are an intelligent assistant that helps users rewrite their queries.
+                        The vectorstore consists of the source code and documentation of a Python library, which enables users to 
+                        programmatically interact with a REST-like API of a software system. The library methods have descriptive 
+                        docstrings. Your task is to rewrite the query in a way that aligns with the language and structure of the 
+                        library's methods and documentation, ensuring optimal retrieval of relevant information.
+
+                        Guidelines for rewriting the query:
+                            1. Identify the main action the user wants to perform (e.g., "Upload a file to a record," "Get users of a group").
+                            2. Remove conversational elements like greetings or pleasantries (e.g., "Hello Chatbot", "I need you to help me with").
+                            3. Exclude specific variable values (e.g., "ID of my record is '31'") unless essential to the intent.
+                            4. Rephrase the query to match the format and keywords used in the docstrings, focusing on verbs and objects relevant to the action (e.g., "Add a record to a collection").
+                            5. Given the query the user might need more than one method to achieve his goal. 
+
+                                Examples:
+                                - User query: "Create a Python script with a method that facilitates the creation of records. This method should accept an array of identifiers as a parameter and allow metadata to be added to each record."
+                                - Rewritten query: "create records, add metadata to record"
+                                - User query: "Hi, can you help me write Python code to add a record to a collection? The record ID is '45', and the collection ID is '12'."
+                                  Rewritten query: "add a record to a collection"
+                                - User query: "I have a folder with files in my local disc and i need a python script with which i can upload the files to a record. The id of the record is 324. The path to the folder is: "C:\Users\Anwender\Documents\League of Legends"
+                                  Rewritten query: "upload files to a record"
+
+                                Based on these examples and guidelines, rewrite the following user query to align more effectively with the keywords used in the docstrings.
+                                Original query:
+                                {query}
+
+                                Rewritten query:"""
 
+    
+    rewritten_query_response = llm.invoke(rewrite_prompt)
+    rewritten_query = rewritten_query_response.content.strip()
 
     kadi_apy_docs = retrieve_within_kadiApy_docs (vector_store, query, k = 5)       
     kadi_apy_library_docs = retrieve_within_kadiApy_library (vector_store, query, k = 10)