Switching to metadata version

app.py

@@ -17,133 +17,10 @@ from llama_index.llms import OpenAI
 llm = OpenAI(temperature=0, model="gpt-3.5-turbo")
 service_context = ServiceContext.from_defaults(llm=llm)
 
-arv_index = load_index_from_storage(StorageContext.from_defaults(persist_dir = "./arv/"))
-# arv_summary_index = load_index_from_storage(StorageContext.from_defaults(persist_dir = "./arv_summary/"))
-arv_vector_query_engine = arv_index.as_query_engine(similarity_top_k = 3)
-# arv_summary_query_engine = arv_summary_index.as_query_engine()
-
-nishauri_index = load_index_from_storage(StorageContext.from_defaults(persist_dir = "./nishauri/"))
-# nishauri_summary_index = load_index_from_storage(StorageContext.from_defaults(persist_dir = "./nishauri_summary/"))
-nishauri_vector_query_engine = nishauri_index.as_query_engine(similarity_top_k = 3)
-# nishauri_summary_query_engine = nishauri_summary_index.as_query_engine()
-
-from llama_index.agent import OpenAIAgent
-
-agents = {}
-
-# define tools
-query_engine_tools = [
-    QueryEngineTool(
-        query_engine=arv_vector_query_engine,
-        metadata=ToolMetadata(
-            name="arv_vector_tool",
-            description=(
-                "Useful for retrieving specific context about HIV care and treatment."
-            ),
-        ),
-    ),
-    # QueryEngineTool(
-    #     query_engine=arv_summary_query_engine,
-    #     metadata=ToolMetadata(
-    #         name="arv_summary_tool",
-    #         description=(
-    #             "Useful for summarization questions related to HIV care and treatment."
-    #         ),
-    #     ),
-    # ),
-]
-
-# build agent
-function_llm = OpenAI(model="gpt-3.5-turbo-0613", temperature = 0)
-agent = OpenAIAgent.from_tools(
-    query_engine_tools,
-    llm=function_llm,
-    verbose=True,
-)
-
-agents["arv"] = agent
-
-# define tools
-query_engine_tools = [
-    QueryEngineTool(
-        query_engine=nishauri_vector_query_engine,
-        metadata=ToolMetadata(
-            name="nishauri_vector_tool",
-            description=(
-                "Useful for retrieving specific context about the Nishauri mobile application through which users are asking questions"
-            ),
-        ),
-    ),
-    # QueryEngineTool(
-    #     query_engine=nishauri_summary_query_engine,
-    #     metadata=ToolMetadata(
-    #         name="nishauri_summary_tool",
-    #         description=(
-    #             "Useful for summarization questions related to the Nishauri mobile application through which users are asking questions"
-    #         ),
-    #     ),
-    # ),
-]
-
-# build agent
-function_llm = OpenAI(model="gpt-3.5-turbo-0613", temperature = 0)
-agent = OpenAIAgent.from_tools(
-    query_engine_tools,
-    llm=function_llm,
-    verbose=True,
-)
-
-agents["nishauri"] = agent
-
-# define top-level nodes
-nodes = []
-
-arv_summary = (
-    "This content contains care and treatment guidance for people living with HIV."
-    " Use this source to answer questions about ARV medications, side effects from medication,"
-    " understanding viral loads, and any question about HIV care and treatment."
-    " This is the default source to use for answering any question that isn't about how to find"
-    " information in the Nishauri app."
-)
-node = IndexNode(text=arv_summary, index_id="arv")
-nodes.append(node)
-
-nishauri_summary = (
-    "This content contains guidance on the Nishauri mobile application through which users are asking questions."
-    " Reference this document when users ask questions such as how to find their viral load"
-    " or lab histories, how to find their appointment histories,"
-    " and want to know how to change their upcoming appointments."
-    " Do not use this to answer any other questions."
-)
-node = IndexNode(text=nishauri_summary, index_id="nishauri")
-nodes.append(node)
-
-# define top-level retriever
-vector_index = VectorStoreIndex(nodes)
-vector_retriever = vector_index.as_retriever(similarity_top_k=1)
-
-# define recursive retriever
-from llama_index.retrievers import RecursiveRetriever
-from llama_index.query_engine import RetrieverQueryEngine
-from llama_index.response_synthesizers import get_response_synthesizer
-
-# note: can pass `agents` dict as `query_engine_dict` since every agent can be used as a query engine
-recursive_retriever = RecursiveRetriever(
-    "vector",
-    retriever_dict={"vector": vector_retriever},
-    query_engine_dict=agents,
-    verbose=True,
-)
-
-response_synthesizer = get_response_synthesizer(
-    # service_context=service_context,
-    response_mode="compact",
-)
-query_engine = RetrieverQueryEngine.from_args(
-    recursive_retriever,
-    response_synthesizer=response_synthesizer,
-    service_context=service_context,
-)
+PERSIST_DIR = "arv_metadata"
+storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
+index = load_index_from_storage(storage_context)
+query_engine = index.as_query_engine(similarity_top_k=3, llm=OpenAI(model="gpt-3.5-turbo"))
 
 
 preamble = (" The person asking the following prompt is a person living with HIV in Kenya."