LlamaIndex
Log in

Find answers from the community

s
F
Y
a
P
Home
Members
.assets.
.
.assets.
Offline, last seen last month
Joined September 25, 2024
..assets.
·

Hello! I tried asking kapa, but maybe I'

Hello! I tried asking kapa, but maybe I'm on ignore (or, more likely, I did it wrong, lol). Anyway, what I wanted to ask is that many of the PDFs that I'm attempting to ingest are encoded in various formats... for example streamlter [ /ASCII85Decode /FlateDecode ] /Length 16927 /Subtype /Type1C >>

This results in nonsense being ingested when I try to load it. How would I go about detecting and decoding the various encoding formats while ingesting PDFs?
1 comment
.
..assets.
·

going from refine to llm lingua +

going from refine to llm lingua + summarize basically turned a 4.5 minute subquestion chain into <1 minute with the same quality on my pipeline
35 comments
.
L
..assets.
·

Has anyone here used the

Has anyone here used the LongLLMLinguaPostprocessor? It definitely increases the density and quality of information that the LLM retains from the context, but it seems to clobber the metadata, so I can't cite any sources.

Just wondering if anyone is having a similar issue w/ the metadata.
51 comments
.
L
..assets.
·

I keep running into an issue where

I keep running into an issue where whenever I set use_async=True on for my query engine, I encounter an error of asyncio.exceptions.CancelledError

The relevant portions of the stack seem to be

Plain Text
File "/path/to/lib/python3.11/site-packages/llama_index/query_engine/sub_question_query_engine.py", line 226, in _aquery_subq
    response = await query_engine.aquery(question)
...
  File "/path/to/lib/python3.11/site-packages/llama_index/response_synthesizers/refine.py", line 325, in aget_response
    response = await self._agive_response_single(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/path/to/lib/python3.11/site-packages/llama_index/response_synthesizers/refine.py", line 430, in _agive_response_single
    structured_response = await program.acall(
                          ^^^^^^^^^^^^^^^^^^^^
  File "/path/to/lib/python3.11/site-packages/llama_index/response_synthesizers/refine.py", line 79, in acall
    answer = await self._llm.apredict(
...
  File "/path/to/lib/python3.11/site-packages/openai/_base_client.py", line 1536, in post
    return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/path/to/lib/python3.11/site-packages/openai/_base_client.py", line 1315, in request
    return await self._request(
           ^^^^^^^^^^^^^^^^^^^^
  File "/path/to/lib/python3.11/site-packages/openai/_base_client.py", line 1339, in _request
    response = await self._client.send(
98 comments
.
L
f