third commit

earnings_app.py

@@ -29,7 +29,6 @@ import llama_index
 from llama_index.embeddings import OpenAIEmbedding
 from llama_index import ServiceContext
 from llama_index.llms import OpenAI
-from llama_index.ingestion import IngestionPipeline
 from llama_index.node_parser import TokenTextSplitter
 
 set_global_handler("wandb", run_args={"project": "final-project-v1"})
@@ -106,10 +105,6 @@ text_splitter = TokenTextSplitter(
     chunk_size=chunk_size
 )
 
-node_parser_pipeline = IngestionPipeline(
-    transformations=[text_splitter]
-)
-
 storage_context = wandb_callback.load_storage_context(
     artifact_url="llmop/final-project-v1/earnings-index:v0"
 )
@@ -138,20 +133,6 @@ def auto_retrieve_fn(
     response = query_engine.query(query)
     return str(response)
 
-# App
-
-# Pydantic is an easy way to define a schema
-class AutoRetrieveModel(BaseModel):
-    query: str = Field(..., description="natural language query string")
-    filter_key_list: List[str] = Field(
-        ..., description="List of metadata filter field names"
-    )
-    filter_value_list: List[str] = Field(
-        ...,
-        description=(
-            "List of metadata filter field values (corresponding to names specified in filter_key_list)"
-        )
-    )
 
 # Main function to extract information
 def extract_information():
@@ -183,4 +164,4 @@ def extract_information():
 #         res = await extract_information_async(text)
 #         print(res)
 
-    asyncio.run(main())
+    # asyncio.run(main())