### Description
renamed several repository links from `hwchase17` to `langchain-ai`.
### Why
I discovered that the README file in the devcontainer contains an old
repository name, so I took the opportunity to rename the old repository
name in all files within the repository, excluding those that do not
require changes.
### Dependencies
none
### Tag maintainer
@baskaryan
### Twitter handle
[kzk_maeda](https://twitter.com/kzk_maeda)
Adds LangServe package
* Integrate Runnables with Fast API creating Server and a RemoteRunnable
client
* Support multiple runnables for a given server
* Support sync/async/batch/abatch/stream/astream/astream_log on the
client side (using async implementations on server)
* Adds validation using annotations (relying on pydantic under the hood)
-- this still has some rough edges -- e.g., open api docs do NOT
generate correctly at the moment
* Uses pydantic v1 namespace
Known issues: type translation code doesn't handle a lot of types (e.g.,
TypedDicts)
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
`mypy` cannot type-check code that relies on dependencies that aren't
installed.
Eventually we'll probably want to install as many optional dependencies
as possible. However, the full "extended deps" setup for langchain
creates a 3GB cache file and takes a while to unpack and install. We'll
probably want something a bit more targeted.
This is a first step toward something better.
A test file was accidentally dropping a `results.json` file in the
current working directory as a result of running `make test`.
This is undesirable, since we don't want to risk accidentally adding
stray files into the repo if we run tests locally and then do `git add
.` without inspecting the file list very closely.
It seems the caching action was not always correctly recreating
softlinks. At first glance, the softlinks it created seemed fine, but
they didn't always work. Possibly hitting some kind of underlying bug,
but not particularly worth debugging in depth -- we can manually create
the soft links we need.
- Revert "Temporarily disable step that seems to be transiently failing.
(#10234)"
- Refresh shell hashtable and show poetry/python location and version.
Make sure that changes to CI infrastructure get tested on CI before
being merged.
Without this PR, changes to the poetry setup action don't trigger a CI
run and in principle could break `master` when merged.
### 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>
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- Description: a description of the change,
- Issue: the issue # it fixes (if applicable),
- Dependencies: any dependencies required for this change,
- Tag maintainer: for a quicker response, tag the relevant maintainer
(see below),
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. These live is docs/extras
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17, @rlancemartin.
-->
Hi LangChain :) Thank you for such a great project!
I was going through the CONTRIBUTING.md and found a few minor issues.
With this PR:
- All lint and test jobs use the exact same Python + Poetry installation
approach, instead of lints doing it one way and tests doing it another
way.
- The Poetry installation itself is cached, which saves ~15s per run.
- We no longer pass shell commands as workflow arguments to a workflow
that just runs them in a shell. This makes our actions more resilient to
shell code injection.
If y'all like this approach, I can modify the scheduled tests workflow
and the release workflow to use this too.
Update installation instructions to only install test dependencies rather than all dependencies.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
If another push to the same PR or branch happens while its CI 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.
It's possible that langchain-experimental works fine with the latest
*published* langchain, but is broken with the langchain on `master`.
Unfortunately, you can see this is currently the case — this is why this
PR also includes a minor fix for the `langchain` package itself.
We want to catch situations like that *before* releasing a new
langchain, hence this test.
The current timeouts are too long, and mean that if the GitHub cache
decides to act up, jobs get bogged down for 15min at a time. This has
happened 2-3 times already this week -- a tiny fraction of our total
workflows but really annoying when it happens to you. We can do better.
Installing deps on cache miss takes about ~4min, so it's not worth
waiting more than 4min for the deps cache. The black and mypy caches
save 1 and 2min, respectively, so wait only up to that long to download
them.
The previous approach was relying on `_test.yml` taking an input
parameter, and then doing almost completely orthogonal things for each
parameter value. I've separated out each of those test situations as its
own job or workflow file, which eliminated all the special-casing and,
in my opinion, improved maintainability by making it much more obvious
what code runs when.
Using `${{ }}` to construct shell commands is risky, since the `${{ }}`
interpolation runs first and ignores shell quoting rules. This means
that shell commands that look safely quoted, like `echo "${{
github.event.issue.title }}"`, are actually vulnerable to shell
injection.
More details here:
https://github.blog/2023-08-09-four-tips-to-keep-your-github-actions-workflows-secure/
Trusted Publishing is the current best practice for publishing Python
packages. Rather than long-lived secret keys, it uses OpenID Connect
(OIDC) to allow our GitHub runner to directly authenticate itself to
PyPI and get a short-lived publishing token. This locks down publishing
quite a bit:
- There's no long-lived publish key to steal anymore.
- Publishing is *only* allowed via the *specifically designated* GitHub
workflow in the designated repo.
It also is operationally easier: no keys means there's nothing that
needs to be periodically rotated, nothing to worry about leaking, and
nobody can accidentally publish a release from their laptop because they
happened to have PyPI keys set up.
After this gets merged, we'll need to configure PyPI to start expecting
trusted publishing. It's only a few clicks and should only take a
minute; instructions are here:
https://docs.pypi.org/trusted-publishers/adding-a-publisher/
More info:
- https://blog.pypi.org/posts/2023-04-20-introducing-trusted-publishers/
- https://github.com/pypa/gh-action-pypi-publish
This is safer than the prior approach, since it's safe by default: the
release workflows never get triggered for non-merged PRs, so there's no
possibility of a buggy conditional accidentally letting a workflow
proceed when it shouldn't have.
The only loss is that publishing no longer requires a `release` label on
the merged PR that bumps the version. We can add a separate CI step that
enforces that part as a condition for merging into `master`, if
desirable.
I have discovered a bug located within `.github/workflows/_release.yml`
which is the primary cause of continuous integration (CI) errors. The
problem can be solved; therefore, I have constructed a PR to address the
issue.
## The Issue
Access the following link to view the exact errors: [Langhain Release
Workflow](https://github.com/langchain-ai/langchain/actions/workflows/langchain_release.yml)
The instances of these errors take place for **each PR** that updates
`pyproject.toml`, excluding those specifically associated with bumping
PRs.
See below for the specific error message:
```
Error: Error 422: Validation Failed: {"resource":"Release","code":"already_exists","field":"tag_name"}
```
An image of the error can be viewed here:
The `_release.yml` document contains the following if-condition:
```yaml
if: |
${{ github.event.pull_request.merged == true }}
&& ${{ contains(github.event.pull_request.labels.*.name, 'release') }}
```
## The Root Cause
The above job constantly runs as the `if-condition` is always identified
as `true`.
## The Logic
The `if-condition` can be defined as `if: ${{ b1 }} && ${{ b2 }}`, where
`b1` and `b2` are boolean values. However, in terms of condition
evaluation with GitHub Actions, `${{ false }}` is identified as a string
value, thereby rendering it as truthy as per the [official
documentation](https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idif).
I have run some tests regarding this behavior within my forked
repository. You can consult my [debug
PR](https://github.com/zawakin/langchain/pull/1) for reference.
Here is the result of the tests:
|If-Condition|Outcome|
|:--:|:--:|
|`if: true && ${{ false }}`|Execution|
|`if: ${{ false }}` |Skipped|
|`if: true && false` |Skipped|
|`if: false`|Skipped|
|`if: ${{ true && false }}` |Skipped|
In view of the first and second results, we can infer that `${{ false
}}` can only be interpreted as `true` for conditions composed of some
expressions.
It is consistent that the condition of `if: ${{ inputs.working-directory
== 'libs/langchain' }}` works.
It is surprised to be skipped for the second case but it seems the spec
of GitHub Actions 😓
Anyway, the PR would fix these errors, I believe 👍
Could you review this? @hwchase17 or @shoelsch , who is the author of
[PR](https://github.com/langchain-ai/langchain/pull/360).
Ternary operators in GitHub Actions syntax are pretty ugly and hard to
read: `inputs.working-directory == '' && '.' ||
inputs.working-directory` means "if the condition is true, use `'.'` and
otherwise use the expression after the `||`".
This PR performs the ternary as few times as possible, assigning its
outcome to an env var we can then reuse as needed.
Only lint on the min and max supported Python versions.
It's extremely unlikely that there's a lint issue on any version in
between that doesn't show up on the min or max versions.
GitHub rate-limits how many jobs can be running at any one time.
Starting new jobs is also relatively slow, so linting on fewer versions
makes CI faster.
Using `poetry add` to install `pydantic@2.1` was also causing poetry to
change its lockfile. This prevented dependency caching from working:
- When attempting to restore a cache, it would hash the lockfile in git
and use it as part of the cache key. Say this is a cache miss.
- Then, it would attempt to save the cache -- but the lockfile will have
changed, so the cache key would be *different* than the key in the
lookup. So the cache save would succeed, but to a key that cannot be
looked up in the next run -- meaning we never get a cache hit.
In addition to busting the cache, the lockfile update itself is also
non-trivially long, over 30s:
This PR fixes the problems by using `pip` to perform the installation,
avoiding the lockfile change.
The previous caching configuration was attempting to cache poetry venvs
created in the default shared virtualenvs directory. However, all
langchain packages use `in-project = true` for their poetry virtualenv
setup, which moves the venv inside the package itself instead. This
meant that poetry venvs were not being cached at all.
This PR ensures that the venv gets cached by adding the in-project venv
directory to the cached directories list.
It also makes sure that the cache key *only* includes the lockfile being
installed, as opposed to *all lockfiles* (unnecessary cache misses) or
just the *top-level lockfile* (cache hits when it shouldn't).
* PR updates test.yml to test with both pydantic versions
* Code should be refactored to make it easier to do testing in matrix
format w/ packages
* Added steps to assert that pydantic version in the environment is as
expected
Probably the most boring PR to review ;)
Individual commits might be easier to digest
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
**Description: a description of the change**
Fixed `make docs_build` and related scripts which caused errors. There
are several changes.
First, I made the build of the documentation and the API Reference into
two separate commands. This is because it takes less time to build. The
commands for documents are `make docs_build`, `make docs_clean`, and
`make docs_linkcheck`. The commands for API Reference are `make
api_docs_build`, `api_docs_clean`, and `api_docs_linkcheck`.
It looked like `docs/.local_build.sh` could be used to build the
documentation, so I used that. Since `.local_build.sh` was also building
API Rerefence internally, I removed that process. `.local_build.sh` also
added some Bash options to stop in error or so. Futher more added `cd
"${SCRIPT_DIR}"` at the beginning so that the script will work no matter
which directory it is executed in.
`docs/api_reference/api_reference.rst` is removed, because which is
generated by `docs/api_reference/create_api_rst.py`, and added it to
.gitignore.
Finally, the description of CONTRIBUTING.md was modified.
**Issue: the issue # it fixes (if applicable)**
https://github.com/hwchase17/langchain/issues/6413
**Dependencies: any dependencies required for this change**
`nbdoc` was missing in group docs so it was added. I installed it with
the `poetry add --group docs nbdoc` command. I am concerned if any
modifications are needed to poetry.lock. I would greatly appreciate it
if you could pay close attention to this file during the review.
**Tag maintainer**
- General / Misc / if you don't know who to tag: @baskaryan
If this PR needs any additional changes, I'll be happy to make them!
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
### Description:
This PR introduces a new option format_diff to the existing Makefile.
This option allows us to apply the formatting tools (Black and isort)
only to the changed Python and ipynb files since the last commit. This
will make our development process more efficient as we only format the
codes that we modify. Along with this change, comments were added to
make the Makefile more understandable and maintainable.
### Issue:
N/A
### Dependencies:
Add dependency to black.
### Tag maintainer:
@baskaryan
### Twitter handle:
[kzk_maeda](https://twitter.com/kzk_maeda)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Fixes https://github.com/hwchase17/langchain/issues/6172
As described in https://github.com/hwchase17/langchain/issues/6172, I'd
love to help update the dev container in this project.
**Summary of changes:**
- Dev container now builds (the current container in this repo won't
build for me)
- Dockerfile updates
- Update image to our [currently-maintained Python
image](https://github.com/devcontainers/images/tree/main/src/python/.devcontainer)
(`mcr.microsoft.com/devcontainers/python`) rather than the deprecated
image from vscode-dev-containers
- Move Dockerfile to root of repo - in order for `COPY` to work
properly, it needs the files (in this case, `pyproject.toml` and
`poetry.toml`) in the same directory
- devcontainer.json updates
- Removed `customizations` and `remoteUser` since they should be covered
by the updated image in the Dockerfile
- Update comments
- Update docker-compose.yaml to properly point to updated Dockerfile
- Add a .gitattributes to avoid line ending conversions, which can
result in hundreds of pending changes
([info](https://code.visualstudio.com/docs/devcontainers/tips-and-tricks#_resolving-git-line-ending-issues-in-containers-resulting-in-many-modified-files))
- Add a README in the .devcontainer folder and info on the dev container
in the contributing.md
**Outstanding questions:**
- Is it expected for `poetry install` to take some time? It takes about
30 minutes for this dev container to finish building in a Codespace, but
a user should only have to experience this once. Through some online
investigation, this doesn't seem unusual
- Versions of poetry newer than 1.3.2 failed every time - based on some
of the guidance in contributing.md and other online resources, it seemed
changing poetry versions might be a good solution. 1.3.2 is from Jan
2023
---------
Co-authored-by: bamurtaugh <brmurtau@microsoft.com>
Co-authored-by: Samruddhi Khandale <samruddhikhandale@github.com>
# Update contribution guidelines and PR template
This PR updates the contribution guidelines to include more information
on how to handle optional dependencies.
The PR template is updated to include a link to the contribution guidelines document.
# Only run linkchecker on direct changes to docs
This is a stop-gap that will speed up PRs.
Some broken links can slip through if they're embedded in doc-strings
inside the codebase.
But we'll still be running the linkchecker on master.
# Check poetry lock file on CI
This PR checks that the lock file is up to date using poetry lock
--check.
As part of this PR, a new lock file was generated.
# Refactor the test workflow
This PR refactors the tests to run using a single test workflow. This
makes it easier to relaunch failing tests and see in the UI which test
failed since the jobs are grouped together.
## Before submitting
## Who can review?
# Add action to test with all dependencies installed
PR adds a custom action for setting up poetry that allows specifying a
cache key:
https://github.com/actions/setup-python/issues/505#issuecomment-1273013236
This makes it possible to run 2 types of unit tests:
(1) unit tests with only core dependencies
(2) unit tests with extended dependencies (e.g., those that rely on an
optional pdf parsing library)
As part of this PR, we're moving some pdf parsing tests into the
unit-tests section and making sure that these unit tests get executed
when running with extended dependencies.
Update the Dockerfile to use the `$POETRY_HOME` argument to set the
Poetry home directory instead of adding Poetry to the PATH environment
variable.
Add instructions to the `CONTRIBUTING.md` file on how to run tests with
Docker.
Closes https://github.com/hwchase17/langchain/issues/2324
When following the Quick Start instructions in the contributing docs, I
was getting a "WheelFileValidationError" on installation of debugpy
which was blocking the installation of a number of other deps. Google
turned up this [GitHub
issue](https://github.com/microsoft/debugpy/issues/1246) indicating a
regression in Poetry 1.4.1 and workarounds.
This PR updates the contrib docs noting the issue and the workarounds.
Adds release workflow that (1) creates a GitHub release and (2)
publishes built artifacts to PyPI
**Release Workflow**
1. Checkout `master` locally and cut a new branch
1. Run `poetry version <rule>` to version bump (e.g., `poetry version
patch`)
1. Commit changes and push to remote branch
1. Ensure all quality check workflows pass
1. Explicitly tag PR with `release` label
1. Merge to mainline
At this point, a release workflow should be triggered because:
* The PR is closed, targeting `master`, and merged
* `pyproject.toml` has been detected as modified
* The PR had a `release` label
The workflow will then proceed to build the artifacts, create a GitHub
release with release notes and uploaded artifacts, and publish to PyPI.
Example Workflow run:
https://github.com/shoelsch/langchain/actions/runs/3711037455/jobs/6291076898
Example Releases: https://github.com/shoelsch/langchain/releases
--
Note, this workflow is looking for the `PYPI_API_TOKEN` secret, so that
will need to be uploaded to the repository secrets. I tested uploading
as far as hitting a permissions issue due to project ownership in Test
PyPI.
- Add support for local build and linkchecking of docs
- Add GitHub Action to automatically check links before prior to
publication
- Minor reformat of Contributing readme
- Fix existing broken links
Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>
Co-authored-by: Hunter Gerlach <HunterGerlach@users.noreply.github.com>
Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>
This PR has two contributions:
1. Add test for when stop token is found in middle of text
2. Add code coverage tooling and instructions
- Add pytest-cov via poetry
- Add necessary config files
- Add new make instruction for `coverage`
- Update README with coverage guidance
- Update minor README formatting/spelling
Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>
