mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
e494b0a09f
#### Summary
A new approach to loading source code is implemented:
Each top-level function and class in the code is loaded into separate
documents. Then, an additional document is created with the top-level
code, but without the already loaded functions and classes.
This could improve the accuracy of QA chains over source code.
For instance, having this script:
```
class MyClass:
def __init__(self, name):
self.name = name
def greet(self):
print(f"Hello, {self.name}!")
def main():
name = input("Enter your name: ")
obj = MyClass(name)
obj.greet()
if __name__ == '__main__':
main()
```
The loader will create three documents with this content:
First document:
```
class MyClass:
def __init__(self, name):
self.name = name
def greet(self):
print(f"Hello, {self.name}!")
```
Second document:
```
def main():
name = input("Enter your name: ")
obj = MyClass(name)
obj.greet()
```
Third document:
```
# Code for: class MyClass:
# Code for: def main():
if __name__ == '__main__':
main()
```
A threshold parameter is added to control whether small scripts are
split in this way or not.
At this moment, only Python and JavaScript are supported. The
appropriate parser is determined by examining the file extension.
#### Tests
This PR adds:
- Unit tests
- Integration tests
#### Dependencies
Only one dependency was added as optional (needed for the JavaScript
parser).
#### Documentation
A notebook is added showing how the loader can be used.
#### Who can review?
@eyurtsev @hwchase17
---------
Co-authored-by: rlm <pexpresss31@gmail.com>
388 lines
12 KiB
TOML
388 lines
12 KiB
TOML
[tool.poetry]
|
|
name = "langchain"
|
|
version = "0.0.217"
|
|
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}
|
|
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 = "^0.2.6", optional = true}
|
|
qdrant-client = {version = "^1.1.2", 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}
|
|
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 = "^3.6.2", 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}
|
|
psychicapi = {version = "^0.5", optional = true}
|
|
zep-python = {version=">=0.31", optional=true}
|
|
langkit = {version = ">=0.0.1.dev3, <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}
|
|
langchainplus-sdk = ">=0.0.17"
|
|
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 = ">=0.1.6", optional = true}
|
|
streamlit = {version = "^1.18.0", optional = true, python = ">=3.8.1,<3.9.7 || >3.9.7,<4.0"}
|
|
|
|
[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"
|
|
|
|
[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.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 = "^3.2.21"
|
|
weaviate-client = "^3.15.5"
|
|
torch = "^1.0.0"
|
|
chromadb = "^0.3.21"
|
|
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"
|
|
cassandra-driver = "^3.27.0"
|
|
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"
|
|
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",
|
|
"pymongo",
|
|
"weaviate-client",
|
|
"redis",
|
|
"google-api-python-client",
|
|
"google-auth",
|
|
"wolframalpha",
|
|
"qdrant-client",
|
|
"tensorflow-text",
|
|
"pypdf",
|
|
"networkx",
|
|
"nomic",
|
|
"aleph-alpha-client",
|
|
"deeplake",
|
|
"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",
|
|
]
|
|
|
|
# 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",
|
|
"chardet",
|
|
"esprima",
|
|
"jq",
|
|
"pdfminer.six",
|
|
"pgvector",
|
|
"pypdf",
|
|
"pymupdf",
|
|
"pypdfium2",
|
|
"tqdm",
|
|
"lxml",
|
|
"atlassian-python-api",
|
|
"beautifulsoup4",
|
|
"pandas",
|
|
"telethon",
|
|
"psychicapi",
|
|
"zep-python",
|
|
"gql",
|
|
"requests_toolbelt",
|
|
"html2text",
|
|
"py-trello",
|
|
"scikit-learn",
|
|
"streamlit",
|
|
"pyspark",
|
|
"openai"
|
|
]
|
|
|
|
[[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"
|
|
]
|