chatdocs
chatdocs copied to clipboard
marella
Chat with your documents offline using AI.
base) PS C:\AI\ChatDocs> chatdocs download ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │ C:\Conda\lib\site-packages\chatdocs\main.py:23 in download │ │ │ │ 20 │ │ 21 @app.command() │ │ 22 def download(config:...
im trying to have ctransformers use gpu but it won't work. my chatdocs.yml: ```yml ctransformers: model: TheBloke/Wizard-Vicuna-7B-Uncensored-GGML model_file: Wizard-Vicuna-7B-Uncensored.ggmlv3.q4_0.bin model_type: llama config: gpu_layers: 50 llm: ctransformers ```
Is it possible to run models that require 48gb vram by combining two 24gb gpus? Ive tried playing around with the chatdocs.yml file to no avail.
Error handling should be improved when adding documents. At the moment when Pandoc encounters a corrupt file, the entire chatdocs program crashes instead of skipping the corrupt file. This is...
I think conversationalRetrival would be a great feature on this awesome project. https://python.langchain.com/docs/modules/chains/popular/chat_vector_db Unfortunately i am not good enough to make it work, i dont know how to pass the...
Hiya, I followed the readme and got stuck trying to add documents with the error below: `AttributeError: partially initialized module 'charset_normalizer' has no attribute 'md__mypyc' (most likely due to a...
First I want to congraulate the team on one of the most fascinating AI/ML projects I've ever seen! The implications of this are nearly limitless, and I'm so excited to...
Hi there, Great package! I am currently experimenting with chatdocs using a folder with both compatible and non-compatible filetypes. Is it possible that - chatdocs add will only work on...
Thank you very much for the work done! Do you think you could update it to be compatible with the new version of chromadb 0.4.5 that uses SQLite? Thanks so...
Is it possible to define the location chatdocs uses to find the embedding model like we do for the ctransformers? what to try and avoid multiple copies of the model...
