langchain/.github/workflows/langchain_experimental_ci.yml

138 lines
4.0 KiB
YAML
Raw Normal View History

2023-07-21 17:36:28 +00:00
---
name: libs/experimental CI
2023-07-21 17:36:28 +00:00
on:
push:
branches: [ master ]
pull_request:
paths:
- '.github/actions/poetry_setup/action.yml'
- '.github/tools/**'
2023-07-21 17:36:28 +00:00
- '.github/workflows/_lint.yml'
- '.github/workflows/_test.yml'
- '.github/workflows/langchain_experimental_ci.yml'
2023-10-26 22:31:20 +00:00
- 'libs/*'
- 'libs/experimental/**'
2023-07-21 17:36:28 +00:00
workflow_dispatch: # Allows to trigger the workflow manually in GitHub UI
# If another push to the same PR or branch happens while this workflow is still running,
# cancel the earlier run in favor of the next run.
#
# There's no point in testing an outdated version of the code. GitHub only allows
# a limited number of job runners to be active at the same time, so it's better to cancel
# pointless jobs early so that more useful jobs can run sooner.
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
env:
POETRY_VERSION: "1.6.1"
WORKDIR: "libs/experimental"
2023-07-21 17:36:28 +00:00
jobs:
lint:
uses:
./.github/workflows/_lint.yml
with:
working-directory: libs/experimental
2023-10-29 22:50:09 +00:00
langchain-location: ../langchain
2023-07-21 17:36:28 +00:00
secrets: inherit
2023-07-21 17:36:28 +00:00
test:
uses:
./.github/workflows/_test.yml
with:
working-directory: libs/experimental
secrets: inherit
compile-integration-tests:
uses:
./.github/workflows/_compile_integration_test.yml
with:
working-directory: libs/experimental
secrets: inherit
# It's possible that langchain-experimental works fine with the latest *published* langchain,
# but is broken with the langchain on `master`.
#
# We want to catch situations like that *before* releasing a new langchain, hence this test.
test-with-latest-langchain:
runs-on: ubuntu-latest
defaults:
run:
working-directory: ${{ env.WORKDIR }}
strategy:
matrix:
python-version:
- "3.8"
- "3.9"
- "3.10"
- "3.11"
name: test with unpublished langchain - Python ${{ matrix.python-version }}
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
uses: "./.github/actions/poetry_setup"
with:
python-version: ${{ matrix.python-version }}
poetry-version: ${{ env.POETRY_VERSION }}
working-directory: ${{ env.WORKDIR }}
cache-key: unpublished-langchain
- name: Install dependencies
shell: bash
run: |
echo "Running tests with unpublished langchain, installing dependencies with poetry..."
poetry install
echo "Editably installing langchain outside of poetry, to avoid messing up lockfile..."
poetry run pip install -e ../langchain
- name: Run tests
run: make test
Add data anonymizer (#9863) ### Description The feature for anonymizing data has been implemented. In order to protect private data, such as when querying external APIs (OpenAI), it is worth pseudonymizing sensitive data to maintain full privacy. Anonynization consists of two steps: 1. **Identification:** Identify all data fields that contain personally identifiable information (PII). 2. **Replacement**: Replace all PIIs with pseudo values or codes that do not reveal any personal information about the individual but can be used for reference. We're not using regular encryption, because the language model won't be able to understand the meaning or context of the encrypted data. We use *Microsoft Presidio* together with *Faker* framework for anonymization purposes because of the wide range of functionalities they provide. The full implementation is available in `PresidioAnonymizer`. ### Future works - **deanonymization** - add the ability to reverse anonymization. For example, the workflow could look like this: `anonymize -> LLMChain -> deanonymize`. By doing this, we will retain anonymity in requests to, for example, OpenAI, and then be able restore the original data. - **instance anonymization** - at this point, each occurrence of PII is treated as a separate entity and separately anonymized. Therefore, two occurrences of the name John Doe in the text will be changed to two different names. It is therefore worth introducing support for full instance detection, so that repeated occurrences are treated as a single object. ### Twitter handle @deepsense_ai / @MaksOpp --------- Co-authored-by: MaksOpp <maks.operlejn@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-30 17:39:44 +00:00
extended-tests:
runs-on: ubuntu-latest
defaults:
run:
working-directory: ${{ env.WORKDIR }}
strategy:
matrix:
python-version:
- "3.8"
- "3.9"
- "3.10"
- "3.11"
name: Python ${{ matrix.python-version }} extended tests
steps:
- uses: actions/checkout@v4
Add data anonymizer (#9863) ### Description The feature for anonymizing data has been implemented. In order to protect private data, such as when querying external APIs (OpenAI), it is worth pseudonymizing sensitive data to maintain full privacy. Anonynization consists of two steps: 1. **Identification:** Identify all data fields that contain personally identifiable information (PII). 2. **Replacement**: Replace all PIIs with pseudo values or codes that do not reveal any personal information about the individual but can be used for reference. We're not using regular encryption, because the language model won't be able to understand the meaning or context of the encrypted data. We use *Microsoft Presidio* together with *Faker* framework for anonymization purposes because of the wide range of functionalities they provide. The full implementation is available in `PresidioAnonymizer`. ### Future works - **deanonymization** - add the ability to reverse anonymization. For example, the workflow could look like this: `anonymize -> LLMChain -> deanonymize`. By doing this, we will retain anonymity in requests to, for example, OpenAI, and then be able restore the original data. - **instance anonymization** - at this point, each occurrence of PII is treated as a separate entity and separately anonymized. Therefore, two occurrences of the name John Doe in the text will be changed to two different names. It is therefore worth introducing support for full instance detection, so that repeated occurrences are treated as a single object. ### Twitter handle @deepsense_ai / @MaksOpp --------- Co-authored-by: MaksOpp <maks.operlejn@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-08-30 17:39:44 +00:00
- name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
uses: "./.github/actions/poetry_setup"
with:
python-version: ${{ matrix.python-version }}
poetry-version: ${{ env.POETRY_VERSION }}
working-directory: libs/experimental
cache-key: extended
- name: Install dependencies
shell: bash
run: |
echo "Running extended tests, installing dependencies with poetry..."
poetry install -E extended_testing
- name: Run extended tests
run: make extended_tests
- name: Ensure the tests did not create any additional files
shell: bash
run: |
set -eu
STATUS="$(git status)"
echo "$STATUS"
# grep will exit non-zero if the target message isn't found,
# and `set -e` above will cause the step to fail.
echo "$STATUS" | grep 'nothing to commit, working tree clean'