issuegpt
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (10.3%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: A854949
- License: apache-2.0
- Language: Python
- Default Branch: main
- Size: 2.64 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
IssueGPT
Issue is an advanced AI-driven tool designed to enhance the efficiency and accuracy of troubleshooting within computer product testing . This system utilizes state-of-the-art Large Language Models (LLMs) to analyze complex issues, predict root causes based on historical data, and suggest viable solutions.
Prerequisite
- WSL
- CUDA
- CONDA
Installation
Clone IssueGPT repository
git clone https://github.com/A854949/IssueGPT.git cd IssueGPTClone llama.cpp repository
git clone https://github.com/ggerganov/llama.cpp cd llama.cpp makeInstall Python 3.11
conda create -n IssueGPT python=3.11 conda activate IssueGPTModify IssueGPT/settings.yaml - local to specific your model name
poetry install --with ui poetry install --with localRun
python scripts/setupto download your modelAfter that running the following command in the repository will install llama.cpp with GPU support:
CMAKE_ARGS='-DLLAMA_CUBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-pythonCreate folder and put your data inside, and run
make ingest $above_folder_pathOnce installed, you can run IssueGPT with the following command:
PGPT_PROFILES=local make runIf your installation was correct, you should see a message similar to the following next time you start the server
BLAS = 1.The UI will be available at http://localhost:8001
Owner
- Name: Mika Shih
- Login: A854949
- Kind: user
- Repositories: 1
- Profile: https://github.com/A854949
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: PrivateGPT
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Iván
family-names: Martínez Toro
email: ivanmartit@gmail.com
orcid: 'https://orcid.org/0009-0004-5065-2311'
- family-names: Gallego Vico
given-names: Daniel
email: danielgallegovico@gmail.com
orcid: 'https://orcid.org/0009-0006-8582-4384'
- given-names: Pablo
family-names: Orgaz
email: pabloogc+gh@gmail.com
orcid: 'https://orcid.org/0009-0008-0080-1437'
repository-code: 'https://github.com/imartinez/privateGPT'
license: Apache-2.0
date-released: '2023-05-02'
GitHub Events
Total
Last Year
Dependencies
- actions/setup-python v4 composite
- snok/install-poetry v1 composite
- actions/checkout v4 composite
- docker/build-push-action v5 composite
- docker/login-action v3 composite
- docker/metadata-action v5 composite
- actions/checkout v4 composite
- actions/checkout v4 composite
- actions/github-script v4 composite
- actions/setup-node v4 composite
- actions/checkout v4 composite
- actions/setup-node v3 composite
- google-github-actions/release-please-action v3 composite
- actions/stale v8 composite
- ./.github/workflows/actions/install_dependencies * composite
- actions/checkout v3 composite
- actions/upload-artifact v3 composite
- 215 dependencies
- black ^22 develop
- mypy ^1.2 develop
- pre-commit ^2 develop
- pytest ^7 develop
- pytest-asyncio ^0.21.1 develop
- pytest-cov ^3 develop
- ruff ^0 develop
- types-pyyaml ^6.0.12.12 develop
- llama-cpp-python ^0.2.23 local
- numpy 1.26.0 local
- sentence-transformers ^2.2.2 local
- torch >=2.0.0, !=2.0.1, !=2.1.0 local
- transformers ^4.34.0 local
- asyncpg ^0.29.0
- boto3 ^1.28.56
- chromadb ^0.4.13
- fastapi ^0.103.1
- injector ^0.21.0
- llama-index 0.9.3
- pgvector ^0.2.5
- psycopg2-binary ^2.9.9
- pypdf ^3.16.2
- python >=3.11,<3.12
- python-multipart ^0.0.6
- pyyaml ^6.0.1
- qdrant-client ^1.6.9
- sqlalchemy ^2.0.27
- watchdog ^3.0.0
- gradio ^4.19.0 ui