chatdocs
chatdocs copied to clipboard
marella
Chat with your documents offline using AI.
I have been trying to get llama 2 models to function correctly. They start off ok but then all of them goes into a loop with repetitions or gibberish. I...
I'm getting the following error even after running `conda install -c conda-forge langchain` `chatdocs download ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │ /mnt/i/chatdocs/chatdocs/chatdocs/main.py:23 in download │ │ │ │...
Change of import path of Embeddings in langchain in the latest version - 0.0.293 ``` - from langchain.embeddings.base import Embeddings + from langchain.schema.embeddings import Embeddings ``` References - https://github.com/langchain-ai/langchain/releases/tag/v0.0.293 -...
a docker-compose-cpu.yml running llama2 7b or wizard 7b to chat with pdf would be helpful. If you are busy let me know waht changes to make i will do and...
Please implement queuing so it would show that another request is being processed and start as soon as this is finished when it is busy processing another request.
If the user gives too long a prompt the GPU will throw a CUDA out of memory error and the whole PC/server requires rebooting. Does anyone have any suggestions for...
**Overview** I'm attempting to use Radeon GPUs with chatdocs. What I've done below seems to work up to the point I ask a question. I get a segmentation fault now...
1. deploy 2. update db 3. hide document/file name source 4. install to specific folder
I have gotten this up and running. It doesn't seem to return high quality results. I have a powerful machine and a 30,000 document corpus to play with. What are...
