Can you help me retrieve the page number along with the response when querying?

Please stand by @digital_dream64 as I search the knowledge base. I normally take about 20 seconds or so. :wave:

----------------------
To retrieve the page number along with the response when querying using LlamaIndex, you can follow the example provided in the extract from the guide on getting references from PDFs. This involves using the page number metadata in the PDF loader along with indexing/query abstractions to use this information effectively. Here's how you can do it:

1. Install LlamaIndex if you're using a Colab notebook or a similar environment:
   
   Plain Text

   Copy

    %pip install llama-index-llms-openai
    !pip install llama-index
    

1. Load your document and build an index:
   ```python
   from llama_index.core import SimpleDirectoryReader, VectorStoreIndex

reader = SimpleDirectoryReader(input_files=["./data/10k/lyft_2021.pdf"])
data = reader.load_data()
index = VectorStoreIndex.from_documents(data)
python
query_engine = index.as_query_engine(streaming=True, similarity_top_k=3)
python
response = query_engine.query(
"What was the impact of COVID? Show statements in bullet form and show page reference after each statement."
)
response.print_response_stream()
python
for node in response.source_nodes:
print("-----")
text_fmt = node.node.get_content().strip().replace("\n", " ")[:1000]
print(f"Text:\t {text_fmt} ...")
print(f"Metadata:\t {node.node.metadata}")
print(f"Score:\t {node.score:.3f}")
```

This approach allows you to retrieve responses along with the page numbers from which the information was sourced, making it easier to reference the original documents. For more detailed instructions and examples, you might want to refer to the original guide on GitHub ().
----------------------
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
----------------------