Initial commit

.github/dependabot.yml

@@ -0,0 +1,7 @@
+version: 2
+updates:
+  # Maintain dependencies for GitHub Actions
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"

.github/workflows/docs.yml

@@ -0,0 +1,24 @@
+name: docs
+on:
+  push:
+    branches:
+      - main
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: 3.x
+      - uses: actions/cache@v3
+        with:
+          key: ${{ github.ref }}
+          path: .cache
+      - run: pip install mkdocs-macros-plugin
+      - run: pip install mkdocs-material
+      - run: pip install mkdocstrings[python]
+      - run: pip install black
+      - run: mkdocs gh-deploy --force

.github/workflows/wheels.yml

@@ -0,0 +1,77 @@
+name: wheels
+
+on:
+  workflow_dispatch:
+  pull_request:
+  push:
+    branches:
+     - release
+  release:
+    types:
+      - published
+
+jobs:
+  build_sdist:
+    name: Build SDist
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        submodules: true
+
+    - name: Build SDist
+      run: pipx run build --sdist
+
+    - name: Check metadata
+      run: pipx run twine check dist/*
+
+    - uses: actions/upload-artifact@v3
+      with:
+        path: dist/*.tar.gz
+
+
+  build_wheels:
+    name: Wheels on ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+
+    steps:
+    - uses: actions/checkout@v3
+      with:
+        submodules: true
+
+    - run: python3 -m pip install --upgrade build && python3 -m build
+
+    - name: Verify clean directory
+      run: git diff --exit-code
+      shell: bash
+
+    - name: Upload wheels
+      uses: actions/upload-artifact@v3
+      with:
+        path: wheelhouse/*.whl
+
+
+  upload_all:
+    name: Upload if release
+    needs: [build_wheels, build_sdist]
+    runs-on: ubuntu-latest
+    if: github.event_name == 'release' && github.event.action == 'published'
+
+    steps:
+    - uses: actions/setup-python@v4
+      with:
+        python-version: "3.x"
+
+    - uses: actions/download-artifact@v3
+      with:
+        name: artifact
+        path: dist
+
+    - uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        verbose: true
+        password: ${{ secrets.PYPI_API_TOKEN }}

.gitignore

@@ -0,0 +1,148 @@
+build/
+dist/
+_build/
+_generate/
+*.so
+*.py[cod]
+*.egg-info
+*env*
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# vscode
+.vscode
+
+# custom
+.idea
+_docs
+_examples
+src/.idea
+mtests

README.md

@@ -0,0 +1,90 @@
+# AskCode
+
+Ask questions to your code base using the power of LLMs.
+
+# Installation
+
+```shell
+pip install https://github.com/abdeladim-s/askcode
+```
+
+# Usage
+
+```shell
+askcode --help
+
+NAME
+    askcode - Chat with your code base with the power of LLMs.
+
+SYNOPSIS
+    askcode <flags>
+
+DESCRIPTION
+    Chat with your code base with the power of LLMs.
+
+FLAGS
+    -c, --codebase_path=CODEBASE_PATH
+        Type: str
+        Default: '.'
+        path to your codebase
+    --language=LANGUAGE
+        Type: str
+        Default: 'python'
+        programming language ['python', 'javascript'] at the moment
+    -p, --parser_threshold=PARSER_THRESHOLD
+        Type: int
+        Default: 0
+        minimum lines needed to activate parsing (0 by default).
+    --text_splitter_chunk_size=TEXT_SPLITTER_CHUNK_SIZE
+        Type: int
+        Default: 256
+        Maximum size of chunks to return
+    --text_splitter_chunk_overlap=TEXT_SPLITTER_CHUNK_OVERLAP
+        Type: int
+        Default: 50
+        Overlap in characters between chunks
+    --use_HF=USE_HF
+        Type: bool
+        Default: True
+        use hugging face models, if False OpenAI models will be used
+    --llm_model=LLM_MODEL
+        Type: str
+        Default: 'TheBloke/CodeLlama-7B-...
+        Large language model name (HF model name or OpenAI model)
+    -e, --embeddings_model=EMBEDDINGS_MODEL
+        Type: str
+        Default: 'sentence-...
+        Embeddings model (HF model name or OpenAI model)
+    --retriever_search_type=RETRIEVER_SEARCH_TYPE
+        Type: str
+        Default: 'mmr'
+        Defines the type of search that the Retriever should perform. Can be "similarity" (default), "mmr", or "similarity_score_threshold".
+    --retriever_k=RETRIEVER_K
+        Type: int
+        Default: 4
+        Amount of documents to return (Default: 4)
+    -m, --max_new_tokens=MAX_NEW_TOKENS
+        Type: int
+        Default: 50
+        Maximum tokens to generate
+    --temperature=TEMPERATURE
+        Type: float
+        Default: 0.1
+        sampling temperature
+    --top_p=TOP_P
+        Type: float
+        Default: 0.9
+        sampling top_p
+    --repetition_penalty=REPETITION_PENALTY
+        Type: float
+        Default: 1.0
+        sampling repetition_penalty
+    --use_autogptq=USE_AUTOGPTQ
+        Type: bool
+        Default: True
+        Set it to True to use Quantized AutoGPTQ models
+```
+
+# License
+
+MIT