private-gpt
private-gpt copied to clipboard
zylon-ai
Interact with your documents using the power of GPT, 100% privately, no data leaks
minor changes: - I propose to use a logger for debugging purpose, this might be useful if the project grows. - Raise a ValueError exception for incorrect models
Has anybody tried this on a codebase and queried to understand the design, architecture etc
Hello, I have followed all the steps correctly I think and I get this error. Any help would be appreciated. ```Loading documents from source_documents Loaded 3208 documents from source_documents Split...
- Changed _load_documents_ function to use os.walk instead of using glob.glob to search for files in the source directory. It now uses os.walk to traverse through all subdirectories and find...
Cant even install it coz of so many errors im getting when trying to: pip install -r requirements.txt Some of them: ERROR: Failed building wheel for llama-cpp-python ERROR: Could not...
As above. Full path for model and embeddings. M1 Macbook Ventura 13.3.1 16GB memory. ``` llama.cpp: loading model from /Users/xyz123/Programming/GPT-tools/privateGPT/models/ggml-model-q4_0.bin llama.cpp: can't use mmap because tensors are not aligned; convert...
Continuation from commit #56. i have explained in the README.md file that this explains how to implement a custom data set for privateGPT
 I just installed everything perfectly without any problems. But when I try to run I am facing this issue.
If I want to add a dataset.csv, would I be able to use privateGPT to query the dataset and possibly perform some calculations?
