mirror of
https://github.com/imartinez/privateGPT.git
synced 2025-04-27 19:28:38 +00:00
51cc638758
* Dockerize private-gpt * Use port 8001 for local development * Add setup script * Add CUDA Dockerfile * Create README.md * Make the API use OpenAI response format * Truncate prompt * refactor: add models and __pycache__ to .gitignore * Better naming * Update readme * Move models ignore to it's folder * Add scaffolding * Apply formatting * Fix tests * Working sagemaker custom llm * Fix linting * Fix linting * Enable streaming * Allow all 3.11 python versions * Use llama 2 prompt format and fix completion * Restructure (#3) Co-authored-by: Pablo Orgaz <pablo@Pablos-MacBook-Pro.local> * Fix Dockerfile * Use a specific build stage * Cleanup * Add FastAPI skeleton * Cleanup openai package * Fix DI and tests * Split tests and tests with coverage * Remove old scaffolding * Add settings logic (#4) * Add settings logic * Add settings for sagemaker --------- Co-authored-by: Pablo Orgaz <pablo@Pablos-MacBook-Pro.local> * Local LLM (#5) * Add settings logic * Add settings for sagemaker * Add settings-local-example.yaml * Delete terraform files * Refactor tests to use fixtures * Join deltas * Add local model support --------- Co-authored-by: Pablo Orgaz <pablo@Pablos-MacBook-Pro.local> * Update README.md * Fix tests * Version bump * Enable simple llamaindex observability (#6) * Enable simple llamaindex observability * Improve code through linting * Update README.md * Move to async (#7) * Migrate implementation to use asyncio * Formatting * Cleanup * Linting --------- Co-authored-by: Pablo Orgaz <pablo@Pablos-MacBook-Pro.local> * Query Docs and gradio UI * Remove unnecessary files * Git ignore chromadb folder * Async migration + DI Cleanup * Fix tests * Add integration test * Use fastapi responses * Retrieval service with partial implementation * Cleanup * Run formatter * Fix types * Fetch nodes asynchronously * Install local dependencies in tests * Install ui dependencies in tests * Install dependencies for llama-cpp * Fix sudo * Attempt to fix cuda issues * Attempt to fix cuda issues * Try to reclaim some space from ubuntu machine * Retrieval with context * Fix lint and imports * Fix mypy * Make retrieval API a POST * Make Completions body a dataclass * Fix LLM chat message order * Add Query Chunks to Gradio UI * Improve rag query prompt * Rollback CI Changes * Move to sync code * Using Llamaindex abstraction for query retrieval * Fix types * Default to CONDENSED chat mode for contextualized chat * Rename route function * Add Chat endpoint * Remove webhooks * Add IntelliJ run config to gitignore * .gitignore applied * Sync chat completion * Refactor total * Typo in context_files.py * Add embeddings component and service * Remove wrong dataclass from IngestService * Filter by context file id implementation * Fix typing * Implement context_filter and separate from the bool use_context in the API * Change chunks api to avoid conceptual class of the context concept * Deprecate completions and fix tests * Remove remaining dataclasses * Use embedding component in ingest service * Fix ingestion to have multipart and local upload * Fix ingestion API * Add chunk tests * Add configurable paths * Cleaning up * Add more docs * IngestResponse includes a list of IngestedDocs * Use IngestedDoc in the Chunk document reference * Rename ingest routes to ingest_router.py * Fix test working directory for intellij * Set testpaths for pytest * Remove unused as_chat_engine * Add .fleet ide to gitignore * Make LLM and Embedding model configurable * Fix imports and checks * Let local_data folder exist empty in the repository * Don't use certain metadata in LLM * Remove long lines * Fix windows installation * Typos * Update poetry.lock * Add TODO for linux * Script and first version of docs * No jekill build * Fix relative url to openapi json * Change default docs values * Move chromadb dependency to the general group * Fix tests to use separate local_data * Create CNAME * Update CNAME * Fix openapi.json relative path * PrivateGPT logo * WIP OpenAPI documentation metadata * Add ingest script (#11) * Add ingest script * Fix broken name refactor * Add ingest docs and Makefile script * Linting * Move transformers to main dependency * Move torch to main dependencies * Don't load HuggingFaceEmbedding in tests * Fix lint --------- Co-authored-by: Pablo Orgaz <pablo@Pablos-MacBook-Pro.local> * Rename file to camel_case * Commit settings-local.yaml * Move documentation to public docs * Fix docker image for linux * Installation and Running the Server documentation * Move back to docs folder, as it is the only supported by github pages * Delete CNAME * Create CNAME * Delete CNAME * Create CNAME * Improved API documentation * Fix lint * Completions documentation * Updated openapi scheme * Ingestion API doc * Minor doc changes * Updated openapi scheme * Chunks API documentation * Embeddings and Health API, and homogeneous responses * Revamp README with new skeleton of content * More docs * PrivateGPT logo * Improve UI * Update ingestion docu * Update README with new sections * Use context window in the retriever * Gradio Documentation * Add logo to UI * Include Contributing and Community sections to README * Update links to resources in the README * Small README.md updates * Wrap lines of README.md * Don't put health under /v1 * Add copy button to Chat * Architecture documentation * Updated openapi.json * Updated openapi.json * Updated openapi.json * Change UI label * Update documentation * Add releases link to README.md * Gradio avatar and stop debug * Readme update * Clean old files * Remove unused terraform checks * Update twitter link. * Disable minimum coverage * Clean install message in README.md --------- Co-authored-by: Pablo Orgaz <pablo@Pablos-MacBook-Pro.local> Co-authored-by: Iván Martínez <ivanmartit@gmail.com> Co-authored-by: RubenGuerrero <ruben.guerrero@boopos.com> Co-authored-by: Daniel Gallego Vico <daniel.gallego@bq.com>
141 lines
3.1 KiB
TOML
141 lines
3.1 KiB
TOML
[tool.poetry]
|
|
name = "private-gpt"
|
|
version = "0.1.0"
|
|
description = "Private GPT"
|
|
authors = ["Zylon <hi@zylon.ai>"]
|
|
|
|
[tool.poetry.dependencies]
|
|
python = ">=3.11,<3.13"
|
|
fastapi = { extras = ["all"], version = "^0.103.1" }
|
|
loguru = "^0.7.2"
|
|
boto3 = "^1.28.56"
|
|
injector = "^0.21.0"
|
|
pyyaml = "^6.0.1"
|
|
python-multipart = "^0.0.6"
|
|
pypdf = "^3.16.2"
|
|
llama-index = "v0.8.35"
|
|
chromadb = "^0.4.13"
|
|
watchdog = "^3.0.0"
|
|
transformers = "^4.34.0"
|
|
torch = "^2.1.0"
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
black = "^22"
|
|
mypy = "^1.2"
|
|
pre-commit = "^2"
|
|
pytest = "^7"
|
|
pytest-cov = "^3"
|
|
ruff = "^0"
|
|
pytest-asyncio = "^0.21.1"
|
|
types-pyyaml = "^6.0.12.12"
|
|
|
|
# Dependencies for gradio UI
|
|
[tool.poetry.group.ui]
|
|
optional = true
|
|
[tool.poetry.group.ui.dependencies]
|
|
gradio = "^3.45.2"
|
|
|
|
[tool.poetry.group.local]
|
|
optional = true
|
|
[tool.poetry.group.local.dependencies]
|
|
sentence-transformers = "^2.2.2"
|
|
numpy = "1.26.0"
|
|
llama-cpp-python = "^0.2.11"
|
|
|
|
[build-system]
|
|
requires = ["poetry-core>=1.0.0"]
|
|
build-backend = "poetry.core.masonry.api"
|
|
|
|
# Packages configs
|
|
|
|
## coverage
|
|
|
|
[tool.coverage.run]
|
|
branch = true
|
|
|
|
[tool.coverage.report]
|
|
skip_empty = true
|
|
precision = 2
|
|
|
|
## black
|
|
|
|
[tool.black]
|
|
target-version = ['py311']
|
|
|
|
## ruff
|
|
# Recommended ruff config for now, to be updated as we go along.
|
|
[tool.ruff]
|
|
target-version = 'py311'
|
|
|
|
# See all rules at https://beta.ruff.rs/docs/rules/
|
|
select = [
|
|
"E", # pycodestyle
|
|
"W", # pycodestyle
|
|
"F", # Pyflakes
|
|
"B", # flake8-bugbear
|
|
"C4", # flake8-comprehensions
|
|
"D", # pydocstyle
|
|
"I", # isort
|
|
"SIM", # flake8-simplify
|
|
"TCH", # flake8-type-checking
|
|
"TID", # flake8-tidy-imports
|
|
"Q", # flake8-quotes
|
|
"UP", # pyupgrade
|
|
"PT", # flake8-pytest-style
|
|
"RUF", # Ruff-specific rules
|
|
]
|
|
|
|
ignore = [
|
|
"E501", # "Line too long"
|
|
# -> line length already regulated by black
|
|
"PT011", # "pytest.raises() should specify expected exception"
|
|
# -> would imply to update tests every time you update exception message
|
|
"SIM102", # "Use a single `if` statement instead of nested `if` statements"
|
|
# -> too restrictive,
|
|
"D100",
|
|
"D101",
|
|
"D102",
|
|
"D103",
|
|
"D104",
|
|
"D105",
|
|
"D106",
|
|
"D107"
|
|
# -> "Missing docstring in public function too restrictive"
|
|
]
|
|
|
|
[tool.ruff.pydocstyle]
|
|
# Automatically disable rules that are incompatible with Google docstring convention
|
|
convention = "google"
|
|
|
|
[tool.ruff.pycodestyle]
|
|
max-doc-length = 88
|
|
|
|
[tool.ruff.flake8-tidy-imports]
|
|
ban-relative-imports = "all"
|
|
|
|
[tool.ruff.flake8-type-checking]
|
|
strict = true
|
|
runtime-evaluated-base-classes = ["pydantic.BaseModel"]
|
|
# Pydantic needs to be able to evaluate types at runtime
|
|
# see https://pypi.org/project/flake8-type-checking/ for flake8-type-checking documentation
|
|
# see https://beta.ruff.rs/docs/settings/#flake8-type-checking-runtime-evaluated-base-classes for ruff documentation
|
|
|
|
[tool.ruff.per-file-ignores]
|
|
# Allow missing docstrings for tests
|
|
"tests/**/*.py" = ["D1"]
|
|
|
|
## mypy
|
|
|
|
[tool.mypy]
|
|
python_version = "3.11"
|
|
strict = true
|
|
check_untyped_defs = false
|
|
explicit_package_bases = true
|
|
exclude = ["tests"]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|
|
addopts = [
|
|
"--import-mode=importlib",
|
|
] |