Update app.py

app.py

@@ -255,45 +255,96 @@ def setup_llm(model_name, temperature, api_key):
     return llm
 
 def retrieve_from_vectorstore(vectorstore, query, k):
-    results = vectorstore.similarity_search(query, k=k)
-    chunks_with_references = [(result.page_content, result.metadata["source"]) for result in results]
-    # Print the chosen chunks and their sources to the console
-    print("\nChosen chunks and their sources for the query:")
-    for chunk, source in chunks_with_references:
-        print(f"Source: {source}\nChunk: {chunk}\n")
-        print("-" * 50)
-    return chunks_with_references
+    retrieved_docs = vectorstore.similarity_search(query, k=k)    
+    return retrieved_docs
+
+
+
+def retrieve_within_kadiApy_docs(vectorstore, query, k):
+    filter_criteria = {"usage": "docs"}
+    retrieved_docs = vectorstore.similarity_search(query=query, k=k, filter=filter_criteria)
+    return retrieved_docs
+
+def retrieve_within_kadiApy_library(vectorstore, query, k):
+    filter_criteria = {"usage": "library", "visibility" : "public"}
+    retrieved_docs = vectorstore.similarity_search(query=query, k=k, filter=filter_criteria)
+    return retrieved_docs
+
+def retrieve_within_kadiApy_cli_library(vectorstore, query, k):
+    filter_criteria = {"usage": "cli_library", "visibility" : "public"}
+    retrieved_docs = vectorstore.similarity_search(query=query, k=k, filter=filter_criteria)
+    return retrieved_docs
+
+def retrieve_within_kadiApy_cli_library_excluding_cli_commands(vectorstore, query, k):
+    filter_criteria = {"usage": "cli_library", "visibility" : "public"}
+    retrieved_docs = vectorstore.similarity_search(query=query, k=k, filter=filter_criteria)
+    filtered_docs = [doc for doc in documents if "command" not in doc.metadata]
+    return filtered_docs
+    
+    
+def retrieve_kadiApy_cli_commands(vectorstore, query, k):
+    filter_criteria = {"usage": "cli_library", "type": "command"}
+    results = vectorstore.similarity_search(query=query, k=k, filter=filter_criteria)
+    return results
+
 
 
 def retrieve_docs_from_vectorstore(vectorstore, query, k): 
     return vectorstore.similarity_search(query, k=k)
 
-def format_doc_context(docs):
-    doc_context = "\n\n".join(doc.page_content for doc in docs)
+
+
+
+def format_kadi_apy_library_context(docs):
+    doc_context_list = []
+    
+    for doc in docs:
+        # Extract metadata information
+        class_info = doc.metadata.get("class", "Unknown Class")
+        type_info = doc.metadata.get("type", "Unknown Type")
+        source_info = doc.metadata.get("source", "Unknown Type")
+        # Format metadata and document content
+        formatted_doc = f"# source: {source_info}\n# class: {class_info}\n# type: {type_info}\n{doc.page_content}\n\n\n"
+        doc_context_list.append(formatted_doc)
     
-    print("\nDocument Context for LLM:\n")
-    print(doc_context)  # Optional: Print the context for verification
+    # Join all formatted document contexts
+    doc_context = "".join(doc_context_list)
     
     return doc_context
 
+
+def format_kadi_api_doc_context(docs):
+    doc_context_list = []
+
+    for doc in docs 
+        source_info = doc.metadata.get("source", "Unknown Type")
+        formatted_doc = f"# source: {source_info}\n{doc.page_content}\n\n\n"
+        doc_context_list.append(formatted_doc)
+    
+    return doc_context
+
+
+                   
 def rag_workflow(query):
     
-    retrieved_doc_chunks = retrieve_from_vectorstore (docstore, query, k=5)
-    retrieved_code_chunks = retrieve_from_vectorstore(codestore, query, k=5)
+  #  retrieved_doc_chunks = retrieve_from_vectorstore (docstore, query, k=5)
+  #  retrieved_code_chunks = retrieve_from_vectorstore(codestore, query, k=5)
 
    # docs = retrieve_docs_from_vectorstore(docstore, query, k=5)
+
+
     
-   # doc_context = format_doc_context(docs) 
-      
-    doc_context = "\n\n".join([doc_chunk for doc_chunk, _ in retrieved_doc_chunks])
-    code_context = "\n\n".join([code_chunk for code_chunk, _ in retrieved_code_chunks]) 
+    kadi_apy_docs = retrieve_within_kadiApy_docs (docstore, query, k = 5)
+    kadi_apy_library_docs = retrieve_within_kadiApy_library (docstore, query, k = 10)
+
+    doc_context = format_kadi_api_doc_context(kadi_apy_docs)
+    code_context = format_kadi_apy_library_context(kadi_apy_library_docs)
 
-    doc_references = "\n".join([f"[{i+1}] {ref}" for i, (_, ref) in enumerate(retrieved_doc_chunks)])
-    code_references = "\n".join([f"[{i+1}] {ref}" for i, (_, ref) in enumerate(retrieved_code_chunks)])
+    
     print(doc_context)
     print(code_context)
-    print(doc_references)
-    print(code_references)
+    
+
     
   #  print("Document Chunks:\n")
   #  print("\n\n".join(["="*80 + "\n" + doc_chunk for doc_chunk, _ in retrieved_doc_chunks]))