atisharma / llama_farm Goto Github PK

tools.hy sort-of-works but is unreliable and could offer something like a plugin system. If it could be made more reliable and performant then it should be made available in the regular chat.

Use faster-whisper to record audio as input.
Use a push-to-talk button

trafilatura looks better for extraction and text processing. This may help remove the reliance on langchain.

Langchain is a quite large and sprawling dependency. It's currently used for:

• document loading (wrapping unstructured)
• document splitting (the document splitters are pretty good)
• wrapping the Chroma and FAISS dbs.

It's simple enough to replace the db wrappers and the loaders could use Unstructured directly, but I'm unsure about the document splitters.

FAISS works well. The Chroma db support should be tested or should be removed. If kept, an options should be presented in the config.

Sumy does extractive text summarisation and is very good. It may be better than Llama for this application.

Some ideas are already in tasks.hy, but it's a quite a hard problem. Other projects are attempting it. Perhaps it should be out of scope?

I have set the openai_api_key and I get:
AuthenticationError: Incorrect API key provided: n/a. You can find your API key at https://platform.openai.com/account/api-keys.
I hardcode the key in place of N/A in the defaults and I get:
InvalidRequestError: Unrecognized request arguments supplied: openai_api_base, openai_api_key

are there problems with the implementation of the API?

Hi,

first of all thank for your great project! Whenever I invoke "/ingest" and regardless of the given input (urls, filnames, dir) it throws an AttributeError, e.g. /ingest "text.txt" will throw

AttributeError: 'list' object has no attribute 'decode'

The trace is barely readable so could you please check if you are having the same issue?
Am I doing something wrong here?

https://facebookresearch.github.io/nougat/
https://github.com/facebookresearch/nougat

Hi there. When I run llama_farm I get this error :

hy.reader.exceptions.LexException: reader macro '#^list' is not defined

Ideas? Thanks