This PR brings a few minor improvements to the docs, namely class/method
docstrings and the demo notebook.
- A note on how to control concurrency levels to tune performance in
bulk inserts, both in the class docstring and the demo notebook;
- Slightly increased concurrency defaults after careful experimentation
(still on the conservative side even for clients running on
less-than-typical network/hardware specs)
- renamed the DB token variable to the standardized
`ASTRA_DB_APPLICATION_TOKEN` name (used elsewhere, e.g. in the Astra DB
docs)
- added a note and a reference (add_text docstring, demo notebook) on
allowed metadata field names.
Thank you!
<!-- 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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
<!-- 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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
<!-- 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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
fix#13356
Add supports following properties for metadata to NotionDBLoader.
- `checkbox`
- `email`
- `number`
- `select`
There are no relevant tests for this code to be updated.
- **Description:** Adds `limit_to_domains` param to the APIChain based
tools (open_meteo, TMDB, podcast_docs, and news_api)
- **Issue:** I didn't open an issue, but after upgrading to 0.0.328
using these tools would throw an error.
- **Dependencies:** N/A
- **Tag maintainer:** @baskaryan
**Note**: I included the trailing / simply because the docs here did
fc886cc303/docs/docs/use_cases/apis.ipynb (L246)
, but I checked the code and it is using `urlparse`. SoI followed the
docs since it comes down to stylee.
Hi,
this PR adds support for OpenAI API v1 for Azure OpenAI completion API.
@baskaryan @hwchase17
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Bumps [pyarrow](https://github.com/apache/arrow) from 13.0.0 to 14.0.1.
<details>
<summary>Commits</summary>
<ul>
<li><a
href="ba53748361"><code>ba53748</code></a>
MINOR: [Release] Update versions for 14.0.1</li>
<li><a
href="529f3768fa"><code>529f376</code></a>
MINOR: [Release] Update .deb/.rpm changelogs for 14.0.1</li>
<li><a
href="b84bbcac64"><code>b84bbca</code></a>
MINOR: [Release] Update CHANGELOG.md for 14.0.1</li>
<li><a
href="f141709763"><code>f141709</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/38607">GH-38607</a>:
[Python] Disable PyExtensionType autoload (<a
href="https://redirect.github.com/apache/arrow/issues/38608">#38608</a>)</li>
<li><a
href="5a37e74198"><code>5a37e74</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/38431">GH-38431</a>:
[Python][CI] Update fs.type_name checks for s3fs tests (<a
href="https://redirect.github.com/apache/arrow/issues/38455">#38455</a>)</li>
<li><a
href="2dcee3f82c"><code>2dcee3f</code></a>
MINOR: [Release] Update versions for 14.0.0</li>
<li><a
href="297428cbf2"><code>297428c</code></a>
MINOR: [Release] Update .deb/.rpm changelogs for 14.0.0</li>
<li><a
href="3e9734f883"><code>3e9734f</code></a>
MINOR: [Release] Update CHANGELOG.md for 14.0.0</li>
<li><a
href="9f90995c8c"><code>9f90995</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/38332">GH-38332</a>:
[CI][Release] Resolve symlinks in RAT lint (<a
href="https://redirect.github.com/apache/arrow/issues/38337">#38337</a>)</li>
<li><a
href="bd61239a32"><code>bd61239</code></a>
<a
href="https://redirect.github.com/apache/arrow/issues/35531">GH-35531</a>:
[Python] C Data Interface PyCapsule Protocol (<a
href="https://redirect.github.com/apache/arrow/issues/37797">#37797</a>)</li>
<li>Additional commits viewable in <a
href="https://github.com/apache/arrow/compare/go/v13.0.0...go/v14.0.1">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the
[Security Alerts
page](https://github.com/langchain-ai/langchain/network/alerts).
</details>
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Predrag Gruevski <2348618+obi1kenobi@users.noreply.github.com>
Hey @rlancemartin, @eyurtsev ,
I did some minimal changes to the `ElasticVectorSearch` client so that
it plays better with existing ES indices.
Main changes are as follows:
1. You can pass the dense vector field name into `_default_script_query`
2. You can pass a custom script query implementation and the respective
parameters to `similarity_search_with_score`
3. You can pass functions for building page content and metadata for the
resulting `Document`
<!-- Thank you for contributing to LangChain!
Replace this 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!
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,
4. an example notebook showing its use.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @dev2049
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @dev2049
- Memory: @hwchase17
- Agents / Tools / Toolkits: @vowelparrot
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
<!-- Thank you for contributing to LangChain!
Replace this 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 you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
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.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
hi!
This is pretty straight-forward: The sdist package does not contain the
license file (which is needed by e.g. conda) because the package is
built from the subdir and can't see the license.
I _copied_ the license but since I'm unfamiliar with the projects
direction, I'm not sure that's correct.
thanks!
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Fixes: #8207
Description:
Pinecone returns scores (not distances) with cosine similarity. The
values according to the docs are [-1, 1], although I could never
reproduce negative values.
This PR ensures that the score returned from Pinecone is preserved,
rather than inverted, so the most relevant documents can be filtered (eg
when using similarity thresholds)
I'll leave this as a draft PR as I couldn't run the tests (my pinecone
account might not be enough - some errors were being thrown around
namespaces) so hopefully someone who _can_ will pick this up.
Maintainers:
@rlancemartin, @eyurtsev
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** Fixed a serialization issue in the add_texts method
of the Matching Engine Vector Store caused by a typo, leading to an
attempt to serialize the json module itself.
- **Issue:** #12154
- **Dependencies:** ./.
- **Tag maintainer:**
Due to the possibility of external inputs including UUIDs, there may be
additional values in **kwargs, while Weaviate's `__init__` method does
not support passing extra **kwarg parameters.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
When calling max_marginal_relevance_search from PGVector the filter
param is not carried over to max_marginal_relevance_search_by_vector
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** Uses `endpoint_url` if provided with a boto3 session.
When running dynamodb locally, credentials are required even if invalid.
With this change, it will be possible to pass a boto3 session with
credentials and specify an endpoint_url
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
<!-- 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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
Replace this entire comment with:
- **Description:** Add MyScaleWithoutJSON which allows user to wrap
columns into Document's Metadata
- **Tag maintainer:** @baskaryan
**Description**
Bumps the Momento dependency to the latest version and refactors the
usage of `SearchHit` in the Momento Vector Index (MVI) vector store
integration. This change is a one liner where we use the preferred
attribute `score` to read the query-document similarity instead of
`distance`. The latest versions of Momento clients will use this
attribute going forward.
**Dependencies**
Updated the Momento dependency to latest version.
**Tests**
💚 I re-ran the existing MVI integration tests
(`tests/integration_tests/vectorstores/test_momento_vector_index.py`)
and they pass.
**Review**
cc @baskaryan @eyurtsev
**Description**
the ollama api now supports passing system prompt and template directly
instead of modifying the model file , but the ollama integration in
langchain did not have this change updated . The update just adds these
two parameters to it ( there are 2 more parameters that are pending to
be updated, I was not sure about their utility wrt to langchain )
Refer :
8713ac23a8
**Issue** : None Applicable
**Dependencies** : None Changed
**Twitter handle** : https://twitter.com/violetto96
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
`_get_kwarg_value` function is useless, one can rely on python builtin
functionalities to do the exact same thing.
- **Description:** Removed `_get_kwarg_value`. Helps with code
readability.
- **Issue:** the issue # it fixes (if applicable),
- **Twitter handle:** @Guillem_96
Improve CSV reader which can't call .strip() on NoneType if there are
less cells in the row compared to the header
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:**
I have a CSV file as followed
```
headerA,headerB,headerC
v1A,v1B,v1C,
v2A,v2B
v3A,v3B,v3C
```
In this case, row 2 is missing a value, which results in reading a None
type. The strip() method can not be called on None, hence raising. In
this PR I am making the change to only call strip if the value if not
None.
- **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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
Added a Docusaurus Loader
Issue: #6353
I had to implement this for working with the Ionic documentation, and
wanted to open this up as a draft to get some guidance on building this
out further. I wasn't sure if having it be a light extension of the
SitemapLoader was in the spirit of a proper feature for the library --
but I'm grateful for the opportunities Langchain has given me and I'd
love to build this out properly for the sake of the community.
Any feedback welcome!
- **Description:** `AzureMLChatOnlineEndpoint` object from
langchain/chat_models/azureml_endpoint.py safe to print
without having any secrets included in raw format in the string
representation.
- **Issue:** #12165,
- **Tag maintainer:** @eyurtsev
---------
Co-authored-by: Faysal Bougamale <faysal.bougamale@horiba.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Adding documentation to the runnable.
- Documentation is not organized in the best way for the runnable; i.e.,
in
terms of LCEL vs. other standard methods, will follow up with more
edits.
**Description:** Removing the single quote wrapper around the table
names in the SQL agent toolkit.py file as it misleads the LLM into
querying against tables with single quotes around their names.
**Issue:** #7457
**Dependencies:** None
**Tag maintainer:** @hwchase17
**Twitter handle:** None
- Implement config_specs to include session_id
- Remove Runnable method and update notebook
- Add more details to notebook, eg. show input schema and config schema
before and after adding message history
---------
Co-authored-by: Harrison Chase <hw.chase.17@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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
This commit fixes the issue that langchain.llms OpenAI completion
stopped working since the V1 openai client update.
Replace this entire comment with:
- **Description:** This PR fixes the issue [AttributeError: module
'openai' has no attribute
'Completion'](https://github.com/langchain-ai/langchain/issues/12967)
similar to
8e0cb2eb84
and https://github.com/langchain-ai/langchain/pull/12969,
- **Issue:** https://github.com/langchain-ai/langchain/issues/12967,
- **Dependencies:** `openai` v1.x.x client,
- **Tag maintainer:** @baskaryan,
- **Twitter handle:** @dosuken123
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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
This adds the response message as a document to the rag retriever so
users can choose to use this. Also drops document limit.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
## Description
We need to centralize the API we use to get the project name for our
tracers. This PR makes it so we always get this from a shared function
in the langsmith sdk.
## Dependencies
Upgraded langsmith from 0.52 to 0.62 to include the new API
`get_tracer_project`
- **Description:**
Recently Chroma rolled out a breaking change on the way we handle
embedding functions, in order to support multi-modal collections.
This broke the way LangChain's `Chroma` objects get created, because we
were passing the EF down into the Chroma collection:
https://docs.trychroma.com/migration#migration-to-0416---november-7-2023
However, internally, we are never actually using embeddings on the
chroma collection - LangChain's `Chroma` object calls it instead. Thus
we just don't pass an `embedding_function` to Chroma itself, which fixes
the issue.
- **Description:** The issue was not listing the proper import error for
amazon textract loader.
- **Issue:** Time wasted trying to figure out what to install...
(langchain docs don't list the dependency either)
- **Dependencies:** N/A
- **Tag maintainer:** @sbusso
- **Twitter handle:** @h9ste
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
# Astra DB Vector store integration
- **Description:** This PR adds a `VectorStore` implementation for
DataStax Astra DB using its HTTP API
- **Issue:** (no related issue)
- **Dependencies:** A new required dependency is `astrapy` (`>=0.5.3`)
which was added to pyptoject.toml, optional, as per guidelines
- **Tag maintainer:** I recently mentioned to @baskaryan this
integration was coming
- **Twitter handle:** `@rsprrs` if you want to mention me
This PR introduces the `AstraDB` vector store class, extensive
integration test coverage, a reworking of the documentation which
conflates Cassandra and Astra DB on a single "provider" page and a new,
completely reworked vector-store example notebook (common to the
Cassandra store, since parts of the flow is shared by the two APIs). I
also took care in ensuring docs (and redirects therein) are behaving
correctly.
All style, linting, typechecks and tests pass as far as the `AstraDB`
integration is concerned.
I could build the documentation and check it all right (but ran into
trouble with the `api_docs_build` makefile target which I could not
verify: `Error: Unable to import module
'plan_and_execute.agent_executor' with error: No module named
'langchain_experimental'` was the first of many similar errors)
Thank you for a review!
Stefano
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Cohere released the new embedding API (Embed v3:
https://txt.cohere.com/introducing-embed-v3/) that treats document and
query embeddings differently. This PR updated the `CohereEmbeddings` to
use them appropriately. It also works with the old models.
Description: This PR masks API key secrets for the Nebula model from
Symbl.ai
Issue: #12165
Maintainer: @eyurtsev
---------
Co-authored-by: Praveen Venkateswaran <praveen.venkateswaran@ibm.com>
* ChatAnyscale was missing coercion to SecretStr for anyscale api key
* The model inherits from ChatOpenAI so it should not force the openai
api key to be secret str until openai model has the same changes
https://github.com/langchain-ai/langchain/issues/12841
Qdrant was incorrectly calculating the cosine similarity and returning
`0.0` for the best match, instead of `1.0`. Internally Qdrant returns a
cosine score from `-1.0` (worst match) to `1.0` (best match), and the
current formula reflects it.
Possibility to pass on_artifacts to a conversation. It can be then
achieved by adding this way:
```python
result = agent.run(
input=message.text,
metadata={
"on_artifact": CALLBACK_FUNCTION
},
)
```
Calls uvicorn directly from cli:
Reload works if you define app by import string instead of object.
(was doing subprocess in order to get reloading)
Version bump to 0.0.14
Remove the need for [serve] for simplicity.
Readmes are updated in #12847 to avoid cluttering this PR
Previously we treated trace_on_chain_group as a command to always start
tracing. This is unintuitive (makes the function do 2 things), and makes
it harder to toggle tracing
When you use a MultiQuery it might be useful to use the original query
as well as the newly generated ones to maximise the changes to retriever
the correct document. I haven't created an issue, it seems a very small
and easy thing.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** Correct number of elements in config list in
`batch()` and `abatch()` of `BaseLLM` in case `max_concurrency` is not
None.
- **Issue:** #12643
- **Twitter handle:** @akionux
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Zep now has the ability to search over chat history summaries. This PR
adds support for doing so. More here: https://blog.getzep.com/zep-v0-17/
@baskaryan @eyurtsev
…s present
<!-- 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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
### Enabling `device_map` in HuggingFacePipeline
For multi-gpu settings with large models, the
[accelerate](https://huggingface.co/docs/accelerate/usage_guides/big_modeling#using--accelerate)
library provides the `device_map` parameter to automatically distribute
the model across GPUs / disk.
The [Transformers
pipeline](3520e37e86/src/transformers/pipelines/__init__.py (L543))
enables users to specify `device` (or) `device_map`, and handles cases
(with warnings) when both are specified.
However, Langchain's HuggingFacePipeline only supports specifying
`device` when calling transformers which limits large models and
multi-gpu use-cases.
Additionally, the [default
value](8bd3ce59cd/libs/langchain/langchain/llms/huggingface_pipeline.py (L72))
of `device` is initialized to `-1` , which is incompatible with the
transformers pipeline when `device_map` is specified.
This PR addresses the addition of `device_map` as a parameter , and
solves the incompatibility of `device = -1` when `device_map` is also
specified.
An additional test has been added for this feature.
Additionally, some existing tests no longer work since
1. `max_new_tokens` has to be specified under `pipeline_kwargs` and not
`model_kwargs`
2. The GPT2 tokenizer raises a `ValueError: Pipeline with tokenizer
without pad_token cannot do batching`, since the `tokenizer.pad_token`
is `None` ([related
issue](https://github.com/huggingface/transformers/issues/19853) on the
transformers repo).
This PR handles fixing these tests as well.
Co-authored-by: Praveen Venkateswaran <praveen.venkateswaran@ibm.com>
[The python
spec](https://docs.python.org/3/reference/datamodel.html#object.__getattr__)
requires that `__getattr__` throw `AttributeError` for missing
attributes but there are several places throwing `ImportError` in the
current code base. This causes a specific problem with `hasattr` since
it calls `__getattr__` then looks only for `AttributeError` exceptions.
At present, calling `hasattr` on any of these modules will raise an
unexpected exception that most code will not handle as `hasattr`
throwing exceptions is not expected.
In our case this is triggered by an exception tracker (Airbrake) that
attempts to collect the version of all installed modules with code that
looks like: `if hasattr(mod, "__version__"):`. With `HEAD` this is
causing our exception tracker to fail on all exceptions.
I only changed instances of unknown attributes raising `ImportError` and
left instances of known attributes raising `ImportError`. It feels a
little weird but doesn't seem to break anything.
- **Description:** Use all Google search results data in SerpApi.com
wrapper instead of the first one only
- **Tag maintainer:** @hwchase17
_P.S. `libs/langchain/tests/integration_tests/utilities/test_serpapi.py`
are not executed during the `make test`._
<!-- 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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
It was passing in message instead of generation
<!-- 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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
* Restrict the chain to specific domains by default
* This is a breaking change, but it will fail loudly upon object
instantiation -- so there should be no silent errors for users
* Resolves CVE-2023-32786
* This is an opt-in feature, so users should be aware of risks if using
jinja2.
* Regardless we'll add sandboxing by default to jinja2 templates -- this
sandboxing is a best effort basis.
* Best strategy is still to make sure that jinja2 templates are only
loaded from trusted sources.
**Description:** Update `langchain.document_loaders.pdf.PyPDFLoader` to
store url in metadata (instead of a temporary file path) if user
provides a web path to a pdf
- **Issue:** Related to #7034; the reporter on that issue submitted a PR
updating `PyMuPDFParser` for this behavior, but it has unresolved merge
issues as of 20 Oct 2023 #7077
- In addition to `PyPDFLoader` and `PyMuPDFParser`, these other classes
in `langchain.document_loaders.pdf` exhibit similar behavior and could
benefit from an update: `PyPDFium2Loader`, `PDFMinerLoader`,
`PDFMinerPDFasHTMLLoader`, `PDFPlumberLoader` (I'm happy to contribute
to some/all of that, including assisting with `PyMuPDFParser`, if my
work is agreeable)
- The root cause is that the underlying pdf parser classes, e.g.
`langchain.document_loaders.parsers.pdf.PyPDFParser`, never receive
information about the url; the parsers receive a
`langchain.document_loaders.blob_loaders.blob`, which contains the pdf
contents and local file path, but not the url
- This update passes the web path directly to the parser since it's
minimally invasive and doesn't require further changes to maintain
existing behavior for local files... bigger picture, I'd consider
extending `blob` so that extra information like this can be
communicated, but that has much bigger implications on the codebase
which I think warrants maintainer input
- **Dependencies:** None
```python
# old behavior
>>> from langchain.document_loaders import PyPDFLoader
>>> loader = PyPDFLoader('https://arxiv.org/pdf/1706.03762.pdf')
>>> docs = loader.load()
>>> docs[0].metadata
{'source': '/var/folders/w2/zx77z1cs01s1thx5dhshkd58h3jtrv/T/tmpfgrorsi5/tmp.pdf', 'page': 0}
# new behavior
>>> from langchain.document_loaders import PyPDFLoader
>>> loader = PyPDFLoader('https://arxiv.org/pdf/1706.03762.pdf')
>>> docs = loader.load()
>>> docs[0].metadata
{'source': 'https://arxiv.org/pdf/1706.03762.pdf', 'page': 0}
```
- **Description:** #12273 's suggestion PR
Like other PDFLoader, loading pdf per each page and giving page
metadata.
- **Issue:** #12273
- **Twitter handle:** @blue0_0hope
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
This will allow you create the schema beforehand. The check was failing
and preventing importing into existing classes.
<!-- 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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
- **Description:** implement [quip](https://quip.com) loader
- **Issue:** https://github.com/langchain-ai/langchain/issues/10352
- **Dependencies:** No
- pass make format, make lint, make test
---------
Co-authored-by: Hao Fan <h_fan@apple.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
latest release broken, this fixes it
---------
Co-authored-by: Roman Vasilyev <rvasilyev@mozilla.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Prior to this PR, `ruff` was used only for linting and not for
formatting, despite the names of the commands. This PR makes it be used
for both linting code and autoformatting it.
This input key was missed in the last update PR:
https://github.com/langchain-ai/langchain/pull/7391
The input/output formats are intended to be like this:
```
{"inputs": [<prompt>]}
{"outputs": [<output_text>]}
```
## Description
This PR adds support for
[lm-format-enforcer](https://github.com/noamgat/lm-format-enforcer) to
LangChain.
The library is similar to jsonformer / RELLM which are supported in
Langchain, but has several advantages such as
- Batching and Beam search support
- More complete JSON Schema support
- LLM has control over whitespace, improving quality
- Better runtime performance due to only calling the LLM's generate()
function once per generate() call.
The integration is loosely based on the jsonformer integration in terms
of project structure.
## Dependencies
No compile-time dependency was added, but if `lm-format-enforcer` is not
installed, a runtime error will occur if it is trying to be used.
## Tests
Due to the integration modifying the internal parameters of the
underlying huggingface transformer LLM, it is not possible to test
without building a real LM, which requires internet access. So, similar
to the jsonformer and RELLM integrations, the testing is via the
notebook.
## Twitter Handle
[@noamgat](https://twitter.com/noamgat)
Looking forward to hearing feedback!
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Best to review one commit at a time, since two of the commits are 100%
autogenerated changes from running `ruff format`:
- Install and use `ruff format` instead of black for code formatting.
- Output of `ruff format .` in the `langchain` package.
- Use `ruff format` in experimental package.
- Format changes in experimental package by `ruff format`.
- Manual formatting fixes to make `ruff .` pass.
I always take 20-30 seconds to re-discover where the
`convert_to_openai_function` wrapper lives in our codebase. Chat
langchain [has no
clue](https://smith.langchain.com/public/3989d687-18c7-4108-958e-96e88803da86/r)
what to do either. There's the older `create_openai_fn_chain` , but we
haven't been recommending it in LCEL. The example we show in the
[cookbook](https://python.langchain.com/docs/expression_language/how_to/binding#attaching-openai-functions)
is really verbose.
General function calling should be as simple as possible to do, so this
seems a bit more ergonomic to me (feel free to disagree). Another option
would be to directly coerce directly in the class's init (or when
calling invoke), if provided. I'm not 100% set against that. That
approach may be too easy but not simple. This PR feels like a decent
compromise between simple and easy.
```
from enum import Enum
from typing import Optional
from pydantic import BaseModel, Field
class Category(str, Enum):
"""The category of the issue."""
bug = "bug"
nit = "nit"
improvement = "improvement"
other = "other"
class IssueClassification(BaseModel):
"""Classify an issue."""
category: Category
other_description: Optional[str] = Field(
description="If classified as 'other', the suggested other category"
)
from langchain.chat_models import ChatOpenAI
llm = ChatOpenAI().bind_functions([IssueClassification])
llm.invoke("This PR adds a convenience wrapper to the bind argument")
# AIMessage(content='', additional_kwargs={'function_call': {'name': 'IssueClassification', 'arguments': '{\n "category": "improvement"\n}'}})
```
- Prefer lambda type annotations over inferred dict schema
- For sequences that start with RunnableAssign infer seq input type as
"input type of 2nd item in sequence - output type of runnable assign"
Replace this entire comment with:
-Add MultiOn close function and update key value and add async
functionality
- solved the key value TabId not found.. (updated to use latest key
value)
@hwchase17
- **Description:** This pull request removes secrets present in raw
format,
- **Issue:** Fireworks api key was exposed when printing out the
langchain object
[#12165](https://github.com/langchain-ai/langchain/issues/12165)
- **Maintainer:** @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description:** Textract PDF Loader generating linearized output,
meaning it will replicate the structure of the source document as close
as possible based on the features passed into the call (e. g. LAYOUT,
FORMS, TABLES). With LAYOUT reading order for multi-column documents or
identification of lists and figures is supported and with TABLES it will
generate the table structure as well. FORMS will indicate "key: value"
with columms.
- **Issue:** the issue fixes#12068
- **Dependencies:** amazon-textract-textractor is added, which provides
the linearization
- **Tag maintainer:** @3coins
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
can get the correct token count instead of using gpt-2 model
**Description:**
Implement get_num_tokens within VertexLLM to use google's count_tokens
function.
(https://cloud.google.com/vertex-ai/docs/generative-ai/get-token-count).
So we don't need to download gpt-2 model from huggingface, also when we
do the mapreduce chain we can get correct token count.
**Tag maintainer:**
@lkuligin
**Twitter handle:**
My twitter: @abehsu1992626
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Following this tutoral about using OpenAI Embeddings with FAISS
https://python.langchain.com/docs/integrations/vectorstores/faiss
```python
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.document_loaders import TextLoader
from langchain.document_loaders import TextLoader
loader = TextLoader("../../../extras/modules/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
```
This works fine
```python
db = FAISS.from_documents(docs, embeddings)
query = "What did the president say about Ketanji Brown Jackson"
docs = db.similarity_search(query)
```
But the async version is not
```python
db = await FAISS.afrom_documents(docs, embeddings) # NotImplementedError
query = "What did the president say about Ketanji Brown Jackson"
docs = await db.asimilarity_search(query) # this will use await asyncio.get_event_loop().run_in_executor under the hood and will not call OpenAIEmbeddings.aembed_query but call OpenAIEmbeddings.embed_query
```
So this PR add async/await supports for FAISS
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
- Description: adding support to Activeloop's DeepMemory feature that
boosts recall up to 25%. Added Jupyter notebook showcasing the feature
and also made index params explicit.
- Twitter handle: will really appreciate if we could announce this on
twitter.
---------
Co-authored-by: adolkhan <adilkhan.sarsen@alumni.nu.edu.kz>
Hey, we're looking to invest more in adding cohere integrations to
langchain so would love to get more of an idea for how it's used.
Hopefully this pr is acceptable. This week I'm also going to be looking
into adding our new [retrieval augmented generation
product](https://txt.cohere.com/chat-with-rag/) to langchain.
---------
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/langchain-ai/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. It lives in `docs/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
## **Description:**
When building our own readthedocs.io scraper, we noticed a couple
interesting things:
1. Text lines with a lot of nested <span> tags would give unclean text
with a bunch of newlines. For example, for [Langchain's
documentation](https://api.python.langchain.com/en/latest/document_loaders/langchain.document_loaders.readthedocs.ReadTheDocsLoader.html#langchain.document_loaders.readthedocs.ReadTheDocsLoader),
a single line is represented in a complicated nested HTML structure, and
the naive `soup.get_text()` call currently being made will create a
newline for each nested HTML element. Therefore, the document loader
would give a messy, newline-separated blob of text. This would be true
in a lot of cases.
<img width="945" alt="Screenshot 2023-10-26 at 6 15 39 PM"
src="https://github.com/langchain-ai/langchain/assets/44193474/eca85d1f-d2bf-4487-a18a-e1e732fadf19">
<img width="1031" alt="Screenshot 2023-10-26 at 6 16 00 PM"
src="https://github.com/langchain-ai/langchain/assets/44193474/035938a0-9892-4f6a-83cd-0d7b409b00a3">
Additionally, content from iframes, code from scripts, css from styles,
etc. will be gotten if it's a subclass of the selector (which happens
more often than you'd think). For example, [this
page](https://pydeck.gl/gallery/contour_layer.html#) will scrape 1.5
million characters of content that looks like this:
<img width="1372" alt="Screenshot 2023-10-26 at 6 32 55 PM"
src="https://github.com/langchain-ai/langchain/assets/44193474/dbd89e39-9478-4a18-9e84-f0eb91954eac">
Therefore, I wrote a recursive _get_clean_text(soup) class function that
1. skips all irrelevant elements, and 2. only adds newlines when
necessary.
2. Index pages (like [this
one](https://api.python.langchain.com/en/latest/api_reference.html))
would be loaded, chunked, and eventually embedded. This is really bad
not just because the user will be embedding irrelevant information - but
because index pages are very likely to show up in retrieved content,
making retrieval less effective (in our tests). Therefore, I added a
bool parameter `exclude_index_pages` defaulted to False (which is the
current behavior — although I'd petition to default this to True) that
will skip all pages where links take up 50%+ of the page. Through manual
testing, this seems to be the best threshold.
## Other Information:
- **Issue:** n/a
- **Dependencies:** n/a
- **Tag maintainer:** n/a
- **Twitter handle:** @andrewthezhou
---------
Co-authored-by: Andrew Zhou <andrew@heykona.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:**
* Add unit tests for document_transformers/beautiful_soup_transformer.py
* Basic functionality is tested (extract tags, remove tags, drop lines)
* add a FIXME comment about the order of tags that is not preserved
(and a passing test, but with the expected tags now out-of-order)
- **Issue:** None
- **Dependencies:** None
- **Tag maintainer:** @rlancemartin
- **Twitter handle:** `peter_v`
Please make sure your PR is passing linting and testing before
submitting.
=> OK: I ran `make format`, `make test` (passing after install of
beautifulsoup4) and `make lint`.
- **Description:** Added masking of the API Key for AI21 LLM when
printed and improved the docstring for AI21 LLM.
- Updated the AI21 LLM to utilize SecretStr from pydantic to securely
manage API key.
- Made improvements in the docstring of AI21 LLM. It now mentions that
the API key can also be passed as a named parameter to the constructor.
- Added unit tests.
- **Issue:** #12165
- **Tag maintainer:** @eyurtsev
---------
Co-authored-by: Anirudh Gautam <anirudh@Anirudhs-Mac-mini.local>
