private-gpt
private-gpt copied to clipboard
Interact with your documents using the power of GPT, 100% privately, no data leaks
- Add `python-dotenv` to requirements file - Address issues related to #133
Guys please help me. Could not load Llama model from path: C:\Users\GaiAA\Documents\privateGPT-main\ggml-model-q4_0.bin
**Operating System:** MacOS 13.3.1 (a) **Hardware:** M1 Max Chip, 64 GByte RAM **Python 3.11.3** **Question: Is below described behavior of ingesting for 4 hours and still going normal ? Or...
Using default settings , built per instructions, but the Linux Machine crashes EVERYTIME at- ingest.py- `llama = LlamaCppEmbeddings(model_path=llama_embeddings_model, n_ctx=model_n_ctx)` Operating System: Kubuntu 23.04 KDE Plasma Version: 5.27.4 KDE Frameworks Version:...
When I get to the step of installing `hnswlib`, I get: ``` Collecting hnswlib>=0.7 (from chromadb==0.3.22->-r requirements.txt (line 3)) Downloading hnswlib-0.7.0.tar.gz (33 kB) Installing build dependencies ... done Getting requirements...
Is it normal that it takes more than 3 hours (and still running) to ingest a file of 200 Kb, which has 1500 lines of text and max 350 characters...
I'd love to use this with filetypes like .eml or .pst for interacting with mail archives. Also, any thoughts on adding something for vision, such as [instructBLIP](https://github.com/salesforce/LAVIS/tree/main/projects/instructblip)?
Apologies if this is not the correct forum, but I am wondering where can I customise the parameters such that the LLM will use only the reference text for answers,...
I keep getting OOM errors while sending prompts. Usually the second prompt gives an OOM error. I'm testing on a MBP from 2019 (intel) w/ 16Gb Ram. How much RAM...
Do I need VS Microsoft C++ Build Tools on Windows to install chromadb and pybind11?