langchain/pyproject.toml
Jeff Huber 2139d0197e
upgrade chroma to 0.4.0 (#7749)
** This should land Monday the 17th ** 

Chroma is upgrading from `0.3.29` to `0.4.0`. `0.4.0` is easier to
build, more durable, faster, smaller, and more extensible. This comes
with a few changes:

1. A simplified and improved client setup. Instead of having to remember
weird settings, users can just do `EphemeralClient`, `PersistentClient`
or `HttpClient` (the underlying direct `Client` implementation is also
still accessible)

2. We migrated data stores away from `duckdb` and `clickhouse`. This
changes the api for the `PersistentClient` that used to reference
`chroma_db_impl="duckdb+parquet"`. Now we simply set
`is_persistent=true`. `is_persistent` is set for you to `true` if you
use `PersistentClient`.

3. Because we migrated away from `duckdb` and `clickhouse` - this also
means that users need to migrate their data into the new layout and
schema. Chroma is committed to providing extension notification and
tooling around any schema and data migrations (for example - this PR!).

After upgrading to `0.4.0` - if users try to access their data that was
stored in the previous regime, the system will throw an `Exception` and
instruct them how to use the migration assistant to migrate their data.
The migration assitant is a pip installable CLI: `pip install
chroma_migrate`. And is runnable by calling `chroma_migrate`

-- TODO ADD here is a short video demonstrating how it works. 

Please reference the readme at
[chroma-core/chroma-migrate](https://github.com/chroma-core/chroma-migrate)
to see a full write-up of our philosophy on migrations as well as more
details about this particular migration.

Please direct any users facing issues upgrading to our Discord channel
called
[#get-help](https://discord.com/channels/1073293645303795742/1129200523111841883).
We have also created a [email
listserv](https://airtable.com/shrHaErIs1j9F97BE) to notify developers
directly in the future about breaking changes.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-18 17:20:54 -07:00

423 lines
13 KiB
TOML

[tool.poetry]
name = "langchain"
version = "0.0.235"
description = "Building applications with LLMs through composability"
authors = []
license = "MIT"
readme = "README.md"
repository = "https://www.github.com/hwchase17/langchain"
[tool.poetry.scripts]
langchain-server = "langchain.server:main"
[tool.poetry.dependencies]
python = ">=3.8.1,<4.0"
pydantic = "^1"
SQLAlchemy = ">=1.4,<3"
requests = "^2"
PyYAML = ">=5.4.1"
numpy = "^1"
azure-core = {version = "^1.26.4", optional=true}
tqdm = {version = ">=4.48.0", optional = true}
openapi-schema-pydantic = "^1.2"
faiss-cpu = {version = "^1", optional = true}
wikipedia = {version = "^1", optional = true}
elasticsearch = {version = "^8", optional = true}
opensearch-py = {version = "^2.0.0", optional = true}
redis = {version = "^4", optional = true}
manifest-ml = {version = "^0.0.1", optional = true}
spacy = {version = "^3", optional = true}
nltk = {version = "^3", optional = true}
transformers = {version = "^4", optional = true}
beautifulsoup4 = {version = "^4", optional = true}
torch = {version = ">=1,<3", optional = true}
jinja2 = {version = "^3", optional = true}
tiktoken = {version = "^0.3.2", optional = true, python="^3.9"}
pinecone-client = {version = "^2", optional = true}
pinecone-text = {version = "^0.4.2", optional = true}
pymongo = {version = "^4.3.3", optional = true}
clickhouse-connect = {version="^0.5.14", optional=true}
weaviate-client = {version = "^3", optional = true}
marqo = {version = "^0.11.0", optional=true}
google-api-python-client = {version = "2.70.0", optional = true}
google-auth = {version = "^2.18.1", optional = true}
wolframalpha = {version = "5.0.0", optional = true}
anthropic = {version = "^0.3", optional = true}
qdrant-client = {version = "^1.3.1", optional = true, python = ">=3.8.1,<3.12"}
dataclasses-json = "^0.5.7"
tensorflow-text = {version = "^2.11.0", optional = true, python = "^3.10, <3.12"}
tenacity = "^8.1.0"
cohere = {version = "^3", optional = true}
openai = {version = "^0", optional = true}
nlpcloud = {version = "^1", optional = true}
nomic = {version = "^1.0.43", optional = true}
huggingface_hub = {version = "^0", optional = true}
octoai-sdk = {version = "^0.1.1", optional = true}
jina = {version = "^3.14", optional = true}
google-search-results = {version = "^2", optional = true}
sentence-transformers = {version = "^2", optional = true}
aiohttp = "^3.8.3"
arxiv = {version = "^1.4", optional = true}
pypdf = {version = "^3.4.0", optional = true}
networkx = {version="^2.6.3", optional = true}
aleph-alpha-client = {version="^2.15.0", optional = true}
deeplake = {version = "^3.6.8", optional = true}
libdeeplake = {version = "^0.0.60", optional = true}
pgvector = {version = "^0.1.6", optional = true}
psycopg2-binary = {version = "^2.9.5", optional = true}
pyowm = {version = "^3.3.0", optional = true}
async-timeout = {version = "^4.0.0", python = "<3.11"}
azure-identity = {version = "^1.12.0", optional=true}
gptcache = {version = ">=0.1.7", optional = true}
atlassian-python-api = {version = "^3.36.0", optional=true}
pytesseract = {version = "^0.3.10", optional=true}
html2text = {version="^2020.1.16", optional=true}
numexpr = "^2.8.4"
duckduckgo-search = {version="^3.8.3", optional=true}
azure-cosmos = {version="^4.4.0b1", optional=true}
lark = {version="^1.1.5", optional=true}
lancedb = {version = "^0.1", optional = true}
pexpect = {version = "^4.8.0", optional = true}
pyvespa = {version = "^0.33.0", optional = true}
O365 = {version = "^2.0.26", optional = true}
jq = {version = "^1.4.1", optional = true}
steamship = {version = "^2.16.9", optional = true}
pdfminer-six = {version = "^20221105", optional = true}
docarray = {version="^0.32.0", extras=["hnswlib"], optional=true}
lxml = {version = "^4.9.2", optional = true}
pymupdf = {version = "^1.22.3", optional = true}
pypdfium2 = {version = "^4.10.0", optional = true}
gql = {version = "^3.4.1", optional = true}
pandas = {version = "^2.0.1", optional = true}
telethon = {version = "^1.28.5", optional = true}
neo4j = {version = "^5.8.1", optional = true}
zep-python = {version=">=0.32", optional=true}
langkit = {version = ">=0.0.6, <0.1.0", optional = true}
chardet = {version="^5.1.0", optional=true}
requests-toolbelt = {version = "^1.0.0", optional = true}
openlm = {version = "^0.0.5", optional = true}
scikit-learn = {version = "^1.2.2", optional = true}
azure-ai-formrecognizer = {version = "^3.2.1", optional = true}
azure-ai-vision = {version = "^0.11.1b1", optional = true}
azure-cognitiveservices-speech = {version = "^1.28.0", optional = true}
py-trello = {version = "^0.19.0", optional = true}
momento = {version = "^1.5.0", optional = true}
bibtexparser = {version = "^1.4.0", optional = true}
singlestoredb = {version = "^0.7.1", optional = true}
pyspark = {version = "^3.4.0", optional = true}
clarifai = {version = ">=9.1.0", optional = true}
tigrisdb = {version = "^1.0.0b6", optional = true}
nebula3-python = {version = "^3.4.0", optional = true}
mwparserfromhell = {version = "^0.6.4", optional = true}
mwxml = {version = "^0.3.3", optional = true}
awadb = {version = "^0.3.3", optional = true}
azure-search-documents = {version = "11.4.0a20230509004", source = "azure-sdk-dev", optional = true}
esprima = {version = "^4.0.1", optional = true}
openllm = {version = ">=0.1.19", optional = true}
streamlit = {version = "^1.18.0", optional = true, python = ">=3.8.1,<3.9.7 || >3.9.7,<4.0"}
psychicapi = {version = "^0.8.0", optional = true}
cassio = {version = "^0.0.7", optional = true}
rdflib = {version = "^6.3.2", optional = true}
sympy = {version = "^1.12", optional = true}
rapidfuzz = {version = "^3.1.1", optional = true}
langsmith = "^0.0.10"
rank-bm25 = {version = "^0.2.2", optional = true}
[tool.poetry.group.docs.dependencies]
autodoc_pydantic = "^1.8.0"
myst_parser = "^0.18.1"
nbsphinx = "^0.8.9"
sphinx = "^4.5.0"
sphinx-autobuild = "^2021.3.14"
sphinx_book_theme = "^0.3.3"
sphinx_rtd_theme = "^1.0.0"
sphinx-typlog-theme = "^0.8.0"
sphinx-panels = "^0.6.0"
toml = "^0.10.2"
myst-nb = "^0.17.1"
linkchecker = "^10.2.1"
sphinx-copybutton = "^0.5.1"
nbdoc = "^0.0.82"
[tool.poetry.group.test.dependencies]
# The only dependencies that should be added are
# dependencies used for running tests (e.g., pytest, freezegun, response).
# Any dependencies that do not meet that criteria will be removed.
pytest = "^7.3.0"
pytest-cov = "^4.0.0"
pytest-dotenv = "^0.5.2"
duckdb-engine = "^0.7.0"
pytest-watcher = "^0.2.6"
freezegun = "^1.2.2"
responses = "^0.22.0"
pytest-asyncio = "^0.20.3"
lark = "^1.1.5"
pandas = "^2.0.0"
pytest-mock = "^3.10.0"
pytest-socket = "^0.6.0"
syrupy = "^4.0.2"
[tool.poetry.group.codespell.dependencies]
codespell = "^2.2.0"
[tool.poetry.group.test_integration]
optional = true
[tool.poetry.group.test_integration.dependencies]
# Do not add dependencies in the test_integration group
# Instead:
# 1. Add an optional dependency to the main group
# poetry add --optional [package name]
# 2. Add the package name to the extended_testing extra (find it below)
# 3. Relock the poetry file
# poetry lock --no-update
# 4. Favor unit tests not integration tests.
# Use the @pytest.mark.requires(pkg_name) decorator in unit_tests.
# Your tests should not rely on network access, as it prevents other
# developers from being able to easily run them.
# Instead write unit tests that use the `responses` library or mock.patch with
# fixtures. Keep the fixtures minimal.
# See CONTRIBUTING.md for more instructions on working with optional dependencies.
# https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md#working-with-optional-dependencies
pytest-vcr = "^1.0.2"
wrapt = "^1.15.0"
openai = "^0.27.4"
elasticsearch = {extras = ["async"], version = "^8.6.2"}
redis = "^4.5.4"
pinecone-client = "^2.2.1"
pinecone-text = "^0.4.2"
pymongo = "^4.3.3"
clickhouse-connect = "^0.5.14"
transformers = "^4.27.4"
deeplake = "^3.6.8"
libdeeplake = "^0.0.60"
weaviate-client = "^3.15.5"
torch = "^1.0.0"
chromadb = "^0.4.0"
tiktoken = "^0.3.3"
python-dotenv = "^1.0.0"
sentence-transformers = "^2"
gptcache = "^0.1.9"
promptlayer = "^0.1.80"
tair = "^1.3.3"
wikipedia = "^1"
cassio = "^0.0.7"
arxiv = "^1.4"
mastodon-py = "^1.8.1"
momento = "^1.5.0"
# Please do not add any dependencies in the test_integration group
# See instructions above ^^
[tool.poetry.group.lint.dependencies]
ruff = "^0.0.249"
types-toml = "^0.10.8.1"
types-redis = "^4.3.21.6"
types-pytz = "^2023.3.0.0"
black = "^23.1.0"
types-chardet = "^5.0.4.6"
mypy-protobuf = "^3.0.0"
[tool.poetry.group.typing.dependencies]
mypy = "^0.991"
types-pyyaml = "^6.0.12.2"
types-requests = "^2.28.11.5"
[tool.poetry.group.dev]
optional = true
[tool.poetry.group.dev.dependencies]
jupyter = "^1.0.0"
playwright = "^1.28.0"
setuptools = "^67.6.1"
[tool.poetry.extras]
llms = ["anthropic", "clarifai", "cohere", "openai", "openllm", "openlm", "nlpcloud", "huggingface_hub", "manifest-ml", "torch", "transformers"]
qdrant = ["qdrant-client"]
openai = ["openai", "tiktoken"]
text_helpers = ["chardet"]
clarifai = ["clarifai"]
cohere = ["cohere"]
docarray = ["docarray"]
embeddings = ["sentence-transformers"]
javascript = ["esprima"]
azure = [
"azure-identity",
"azure-cosmos",
"openai",
"azure-core",
"azure-ai-formrecognizer",
"azure-ai-vision",
"azure-cognitiveservices-speech",
"azure-search-documents",
]
all = [
"anthropic",
"clarifai",
"cohere",
"openai",
"nlpcloud",
"huggingface_hub",
"jina",
"manifest-ml",
"elasticsearch",
"opensearch-py",
"google-search-results",
"faiss-cpu",
"sentence-transformers",
"transformers",
"spacy",
"nltk",
"wikipedia",
"beautifulsoup4",
"tiktoken",
"torch",
"jinja2",
"pinecone-client",
"pinecone-text",
"marqo",
"pymongo",
"weaviate-client",
"redis",
"google-api-python-client",
"google-auth",
"wolframalpha",
"qdrant-client",
"tensorflow-text",
"pypdf",
"networkx",
"nomic",
"aleph-alpha-client",
"deeplake",
"libdeeplake",
"pgvector",
"psycopg2-binary",
"pyowm",
"pytesseract",
"html2text",
"atlassian-python-api",
"gptcache",
"duckduckgo-search",
"arxiv",
"azure-identity",
"clickhouse-connect",
"azure-cosmos",
"lancedb",
"langkit",
"lark",
"pexpect",
"pyvespa",
"O365",
"jq",
"docarray",
"steamship",
"pdfminer-six",
"lxml",
"requests-toolbelt",
"neo4j",
"openlm",
"azure-ai-formrecognizer",
"azure-ai-vision",
"azure-cognitiveservices-speech",
"momento",
"singlestoredb",
"tigrisdb",
"nebula3-python",
"awadb",
"esprima",
"octoai-sdk",
"rdflib",
]
# An extra used to be able to add extended testing.
# Please use new-line on formatting to make it easier to add new packages without
# merge-conflicts
extended_testing = [
"beautifulsoup4",
"bibtexparser",
"cassio",
"chardet",
"esprima",
"jq",
"pdfminer.six",
"pgvector",
"pypdf",
"pymupdf",
"pypdfium2",
"tqdm",
"lxml",
"atlassian-python-api",
"mwparserfromhell",
"mwxml",
"pandas",
"telethon",
"psychicapi",
"zep-python",
"gql",
"requests_toolbelt",
"html2text",
"py-trello",
"scikit-learn",
"streamlit",
"pyspark",
"openai",
"sympy",
"rapidfuzz",
"openai",
"rank_bm25",
]
[[tool.poetry.source]]
name = "azure-sdk-dev"
url = "https://pkgs.dev.azure.com/azure-sdk/public/_packaging/azure-sdk-for-python/pypi/simple/"
secondary = true
[tool.ruff]
select = [
"E", # pycodestyle
"F", # pyflakes
"I", # isort
]
exclude = [
"tests/integration_tests/examples/non-utf8-encoding.py",
]
[tool.mypy]
ignore_missing_imports = "True"
disallow_untyped_defs = "True"
exclude = ["notebooks", "examples", "example_data"]
[tool.coverage.run]
omit = [
"tests/*",
]
[build-system]
requires = ["poetry-core>=1.0.0"]
build-backend = "poetry.core.masonry.api"
[tool.pytest.ini_options]
# --strict-markers will raise errors on unknown marks.
# https://docs.pytest.org/en/7.1.x/how-to/mark.html#raising-errors-on-unknown-marks
#
# https://docs.pytest.org/en/7.1.x/reference/reference.html
# --strict-config any warnings encountered while parsing the `pytest`
# section of the configuration file raise errors.
#
# https://github.com/tophat/syrupy
# --snapshot-warn-unused Prints a warning on unused snapshots rather than fail the test suite.
addopts = "--strict-markers --strict-config --durations=5 --snapshot-warn-unused"
# Registering custom markers.
# https://docs.pytest.org/en/7.1.x/example/markers.html#registering-markers
markers = [
"requires: mark tests as requiring a specific library"
]
[tool.codespell]
skip = '.git,*.pdf,*.svg,*.pdf,*.yaml,*.ipynb,poetry.lock,*.min.js,*.css,package-lock.json,example_data,_dist,examples'
# Ignore latin etc
ignore-regex = '.*(Stati Uniti|Tense=Pres).*'
# whats is a typo but used frequently in queries so kept as is
# aapply - async apply
# unsecure - typo but part of API, decided to not bother for now
ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogyny,unsecure'