add langchain_contrib module

src/langchain_contrib/.dockerignore

@@ -0,0 +1,6 @@
+.venv
+.github
+.git
+.mypy_cache
+.pytest_cache
+Dockerfile

src/langchain_contrib/.flake8

@@ -0,0 +1,12 @@
+[flake8]
+exclude =
+    venv
+    .venv
+    __pycache__
+    notebooks
+# Recommend matching the black line length (default 88),
+# rather than using the flake8 default of 79:
+max-line-length = 88
+extend-ignore =
+    # See https://github.com/PyCQA/pycodestyle/issues/373
+    E203,

src/langchain_contrib/.gitattributes

@@ -0,0 +1,3 @@
+* text=auto eol=lf
+*.{cmd,[cC][mM][dD]} text eol=crlf
+*.{bat,[bB][aA][tT]} text eol=crlf

src/langchain_contrib/.gitignore

@@ -0,0 +1,169 @@
+.vs/
+.vscode/
+.idea/
+# 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/
+docs/docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+notebooks/
+
+# 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
+.envrc
+.venv
+.venvs
+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/
+
+# macOS display setting files
+.DS_Store
+
+# Wandb directory
+wandb/
+
+# asdf tool versions
+.tool-versions
+/.ruff_cache/
+
+*.pkl
+*.bin
+
+# integration test artifacts
+data_map*
+\[('_type', 'fake'), ('stop', None)]
+
+# Replit files
+*replit*
+
+node_modules
+docs/.yarn/
+docs/node_modules/
+docs/.docusaurus/
+docs/.cache-loader/
+docs/_dist
+docs/api_reference/_build
+docs/docs_skeleton/build
+docs/docs_skeleton/node_modules
+docs/docs_skeleton/yarn.lock
+
+sftp-config.json

src/langchain_contrib/.gitmodules

@@ -0,0 +1,4 @@
+[submodule "docs/_docs_skeleton"]
+	path = docs/_docs_skeleton
+	url = https://github.com/langchain-ai/langchain-shared-docs
+	branch = main

src/langchain_contrib/.readthedocs.yaml

@@ -0,0 +1,29 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the version of Python and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.11"
+  jobs:
+    pre_build:
+      - python docs/api_reference/create_api_rst.py
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+   configuration: docs/api_reference/conf.py
+
+# If using Sphinx, optionally build your docs in additional formats such as PDF
+# formats:
+#    - pdf
+
+# Optionally declare the Python requirements required to build your docs
+python:
+   install:
+   - requirements: docs/requirements.txt
+   - method: pip
+     path: .

src/langchain_contrib/Dockerfile

@@ -0,0 +1,48 @@
+# This is a Dockerfile for running unit tests
+
+ARG POETRY_HOME=/opt/poetry
+
+# Use the Python base image
+FROM python:3.11.2-bullseye AS builder
+
+# Define the version of Poetry to install (default is 1.4.2)
+ARG POETRY_VERSION=1.4.2
+
+# Define the directory to install Poetry to (default is /opt/poetry)
+ARG POETRY_HOME
+
+# Create a Python virtual environment for Poetry and install it
+RUN python3 -m venv ${POETRY_HOME} && \
+    $POETRY_HOME/bin/pip install --upgrade pip && \
+    $POETRY_HOME/bin/pip install poetry==${POETRY_VERSION}
+
+# Test if Poetry is installed in the expected path
+RUN echo "Poetry version:" && $POETRY_HOME/bin/poetry --version
+
+# Set the working directory for the app
+WORKDIR /app
+
+# Use a multi-stage build to install dependencies
+FROM builder AS dependencies
+
+ARG POETRY_HOME
+
+# Copy only the dependency files for installation
+COPY pyproject.toml poetry.lock poetry.toml ./
+
+# Install the Poetry dependencies (this layer will be cached as long as the dependencies don't change)
+RUN $POETRY_HOME/bin/poetry install --no-interaction --no-ansi --with test
+
+# Use a multi-stage build to run tests
+FROM dependencies AS tests
+
+# Copy the rest of the app source code (this layer will be invalidated and rebuilt whenever the source code changes)
+COPY . .
+
+RUN /opt/poetry/bin/poetry install --no-interaction --no-ansi --with test
+
+# Set the entrypoint to run tests using Poetry
+ENTRYPOINT ["/opt/poetry/bin/poetry", "run", "pytest"]
+
+# Set the default command to run all unit tests
+CMD ["tests/unit_tests"]

src/langchain_contrib/Makefile

@@ -0,0 +1,73 @@
+.PHONY: all clean format lint test tests test_watch integration_tests docker_tests help extended_tests
+
+all: help
+
+coverage:
+	poetry run pytest --cov \
+		--cov-config=.coveragerc \
+		--cov-report xml \
+		--cov-report term-missing:skip-covered
+
+clean: docs_clean
+
+docs_compile:
+	poetry run nbdoc_build --srcdir $(srcdir)
+
+docs_build:
+	cd docs && poetry run make html
+
+docs_clean:
+	cd docs && poetry run make clean
+
+docs_linkcheck:
+	poetry run linkchecker docs/_build/html/index.html
+
+format:
+	poetry run black .
+	poetry run ruff --select I --fix .
+
+PYTHON_FILES=.
+lint: PYTHON_FILES=.
+lint_diff: PYTHON_FILES=$(shell git diff --name-only --diff-filter=d master | grep -E '\.py$$')
+
+lint lint_diff:
+	poetry run mypy $(PYTHON_FILES)
+	poetry run black $(PYTHON_FILES) --check
+	poetry run ruff .
+
+TEST_FILE ?= tests/unit_tests/
+
+test:
+	poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)
+
+tests: 
+	poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)
+
+extended_tests:
+	poetry run pytest --disable-socket --allow-unix-socket --only-extended tests/unit_tests
+
+test_watch:
+	poetry run ptw --now . -- tests/unit_tests
+
+integration_tests:
+	poetry run pytest tests/integration_tests
+
+docker_tests:
+	docker build -t my-langchain-image:test .
+	docker run --rm my-langchain-image:test
+
+help:
+	@echo '----'
+	@echo 'coverage                     - run unit tests and generate coverage report'
+	@echo 'docs_build                   - build the documentation'
+	@echo 'docs_clean                   - clean the documentation build artifacts'
+	@echo 'docs_linkcheck               - run linkchecker on the documentation'
+	@echo 'format                       - run code formatters'
+	@echo 'lint                         - run linters'
+	@echo 'test                         - run unit tests'
+	@echo 'tests                        - run unit tests'
+	@echo 'test TEST_FILE=<test_file>   - run all tests in file'
+	@echo 'extended_tests               - run only extended unit tests'
+	@echo 'test_watch                   - run unit tests in watch mode'
+	@echo 'integration_tests            - run integration tests'
+	@echo 'docker_tests                 - run unit tests in docker'

src/langchain_contrib/README.md

@@ -0,0 +1,20 @@
+## Repository for langchain's extra modules
+
+This repository is intended for the development of so-called "extra" modules,
+contributed functionality. New modules quite often do not have stable API,
+and they are not well-tested. Thus, they shouldn't be released as a part of the
+official langchain distribution, since the library maintains binary compatibility,
+and tries to provide decent performance and stability.
+
+So, all the new modules should be developed separately, and published in the
+`langchain_contrib` repository at first. Later, when the module matures and gains
+popularity, it will create a pr for langchain.
+
+
+### Update the repository documentation
+
+In order to keep a clean overview containing all contributed modules, the following files need to be created/adapted:
+
+1. Update the README.md file under the modules folder. Here, you add your model with a single-line description.
+
+2. Add a README.md inside your own module folder. This README explains which functionality (separate functions) is available, links to the corresponding samples, and explains in somewhat more detail what the module is expected to do. If any extra requirements are needed to build the module without problems, add them here also.