Commit Graph

10026 Commits (3b3ed72d3516cea6a8df0de274f29c9df33fbb95)
 

Author SHA1 Message Date
liuzc9 41e232cb82
Fix typo in vearch.md (#22840)
Fix typo
2 months ago
Kagura Chen 57783c5e55
Fix: lint errors and update Field alias in models.py and AutoSelectionScorer initialization (#22846)
This PR addresses several lint errors in the core package of LangChain.
Specifically, the following issues were fixed:

1.Unexpected keyword argument "required" for "Field"  [call-arg]
2.tests/integration_tests/chains/test_cpal.py:263: error: Unexpected
keyword argument "narrative_input" for "QueryModel" [call-arg]
2 months ago
Erick Friis 5bc774827b
langchain: release 0.2.4 (#22872) 2 months ago
Erick Friis 7234fd0f51
core: release 0.2.6 (#22868) 2 months ago
Jacob Lee bcbb43480c
core[patch]: Treat type as a special field when merging lists (#22750)
Should we even log a warning? At least for Anthropic, it's expected to
get e.g. `text_block` followed by `text_delta`.

@ccurme @baskaryan @efriis
2 months ago
Nuno Campos bae82e966a
core: In astream_events v2 propagate cancel/break to the inner astream call (#22865)
- previous behavior was for the inner astream to continue running with
no interruption
- also propagate break in core runnable methods
2 months ago
Eugene Yurtsev a766815a99
experimental[patch]/docs[patch]: Update links to security docs (#22864)
Minor update to newest version of security docs (content should be
identical).
2 months ago
Eugene Yurtsev 8f7cc73817
ci: Add script to check for pickle usage in community (#22863)
Add script to check for pickle usage in community.
2 months ago
Eugene Yurtsev 77209f315e
community[patch]: FAISS VectorStore deserializer should be opt-in (#22861)
FAISS deserializer uses pickle module. Users have to opt-in to
de-serialize.
2 months ago
Eugene Yurtsev ce0b0f22a1
experimental[major]: Force users to opt-in into code that relies on the python repl (#22860)
This should make it obvious that a few of the agents in langchain
experimental rely on the python REPL as a tool under the hood, and will
force users to opt-in.
2 months ago
Isaac Francisco 869523ad72
[docs]: added info for TavilySearchResults (#22765) 2 months ago
ccurme 42257b120f
partners: fix numpy dep (#22858)
Following https://github.com/langchain-ai/langchain/pull/22813, which
added python 3.12 to CI, here we update numpy accordingly in partner
packages.
2 months ago
Isaac Francisco 345fd3a556
minor functionality change: adding API functionality to tavilysearch (#22761) 2 months ago
Isaac Francisco 034257e9bf
docs: improved recursive url loader docs (#22648)
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2 months ago
Isaac Francisco e832bbb486
[docs]: bind tools (#22831) 2 months ago
ccurme b626c3ca23
groq[patch]: add usage_metadata to (a)invoke and (a)stream (#22834) 2 months ago
Jacob Lee e01e5d5a91
docs[patch]: Improve Groq integration page (#22844)
Was bare bones and got marked by folks as unhelpful.

CC @efriis @colemccracken
2 months ago
Jacob Lee 12eff6a130
docs[patch]: Readd Pydantic compatibility docs (#22836)
As a how-to guide.

CC @eyurtsev @hwchase17
2 months ago
Jacob Lee cb654a3245
docs[patch]: Adds multimodal column to chat models table, move up in concepts (#22837)
CC @hwchase17 @baskaryan
2 months ago
James Braza 45b394268c
core[patch]: allowing latest `packaging` versions (#22792)
Allowing version 24 of https://github.com/pypa/packaging

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2 months ago
Jacob Lee 00ad197502
docs[patch]: Add structured output to conceptual docs (#22791)
This downgrades `Function/tool calling` from a h3 to an h4 which means
it'll no longer show up in the right sidebar, but any direct links will
still work. I think that is ok, but LMK if you disapprove.

CC @hwchase17 @eyurtsev @rlancemartin
2 months ago
Karim Lalani 276be6cdd4
[experimental][llms][OllamaFunctions] tool calling related fixes (#22339)
Fixes issues with tool calling to handle tool objects correctly. Added
support to handle ToolMessage correctly.
Added additional checks for error conditions.

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
2 months ago
Christophe Bornet d04e899b56
ci: add testing with Python 3.12 (#22813)
We need to use a different version of numpy for py3.8 and py3.12 in
pyproject.
And so do projects that use that Python version range and import
langchain.

    - **Twitter handle:** _cbornet
2 months ago
HyoJin Kang b6bf2bb234
community[patch]: fix database uri type in SQLDatabase (#22661)
**Description**
sqlalchemy uses "sqlalchemy.engine.URL" type for db uri argument.
Added 'URL' type for compatibility.

**Issue**: None

**Dependencies:** None

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2 months ago
Eugene Yurtsev 5dbbdcbf8e
core[patch]: Update remaining root_validators (#22829)
This PR updates the remaining root_validators in core to either be explicit pre-init or post-init validators.
2 months ago
Eugene Yurtsev 265e650e64
community[patch]: Update root_validators embeddings: llamacpp, jina, dashscope, mosaicml, huggingface_hub, Toolkits: Connery, ChatModels: PAI_EAS, (#22828)
This PR updates root validators for:

* Embeddings: llamacpp, jina, dashscope, mosaicml, huggingface_hub
* Toolkits: Connery
* ChatModels: PAI_EAS

Following this issue:
https://github.com/langchain-ai/langchain/issues/22819
2 months ago
JonZeolla 32ba8cfab0
community[minor]: implement huggingface show_progress consistently (#22682)
- **Description:** This implements `show_progress` more consistently
(i.e. it is also added to the `HuggingFaceBgeEmbeddings` object).
- **Issue:** This implements `show_progress` more consistently in the
embeddings huggingface classes. Previously this could have been set via
`encode_kwargs`.
 - **Dependencies:** None
 - **Twitter handle:** @jonzeolla
2 months ago
Eugene Yurtsev 74e705250f
core[patch]: update some root_validators (#22787)
Update some of the @root_validators to be explicit pre=True or
pre=False, skip_on_failure=True for pydantic 2 compatibility.
2 months ago
bincat 3d6e8547f9
docs: fix function name in tutorials/agents.ipynb (#22809)
the function called in the flowing example is `create_react_agent`, not
`create_tool_calling_executor `
2 months ago
mrhbj a1268d9e9a
community[patch]: fix hunyuan message include chinese signature error (#22795) (#22796)
… (#22795)

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: 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/docs/integrations` directory.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
2 months ago
Kagura Chen 513f1d8037
docs: update repo_structure.mdx to reflect latest code changes (#22810)
**Description:** This PR updates the documentation to reflect the recent
code changes.

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2 months ago
Mr. Lance E Sloan «UMich» 08c466c603
community[patch]: bugfix for `YoutubeLoader`'s `LINES` format (#22815)
- **Description:** A change I submitted recently introduced a bug in
`YoutubeLoader`'s `LINES` output format. In those conditions, curly
braces ("`{}`") creates a set, not a dictionary. This bugfix explicitly
specifies that a dictionary is created.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter:** lsloan_umich
- **Mastodon:**
[lsloan@mastodon.social](https://mastodon.social/@lsloan)
2 months ago
Philippe PRADOS 23c22fcbc9
langchain[minor]: Make EmbeddingsFilters async (#22737)
Add native async implementation for EmbeddingsFilter
2 months ago
endrajeet b45bf78d2e
Update index.mdx (#22818)
changed "# 🌟Recognition" to "### 🌟 Recognition" to match the rest of the
subheadings.

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: 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/docs/integrations` directory.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
2 months ago
Bagatur 8203c1ff87
infra: lint new docs to match templates (#22786) 3 months ago
ccurme 936aedd10c
mistral[patch]: add usage_metadata to (a)invoke and (a)stream (#22781) 3 months ago
Jiří Spilka 20e3662acf
docs: Correct code examples in the Apify's notebooks (#22768)
**Description:** Correct code examples in the Apify document load
notebook and Apify Dataset notebook

**Issue**: None
**Dependencies**: None
**Twitter handle**: None
3 months ago
mrhbj 9212c9fcb8
community[patch]: fix hunyuan client json analysis (#22452) (#22767)
Thank you for contributing to LangChain!

- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [x] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [x] **Add tests and docs**: 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/docs/integrations` directory.


- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
3 months ago
Rohan Aggarwal 86e8224cf1
community[patch]: Support for old clients (Thin and Thick) Oracle Vector Store (#22766)
Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
Support for old clients (Thin and Thick) Oracle Vector Store


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
Support for old clients (Thin and Thick) Oracle Vector Store

- [ ] **Add tests and docs**: If you're adding a new integration, please
include
Have our own local tests

---------

Co-authored-by: rohan.aggarwal@oracle.com <rohaagga@phoenix95642.dev3sub2phx.databasede3phx.oraclevcn.com>
3 months ago
Jacob Lee 232908a46d
docs[patch]: Adds streaming conceptual doc (#22760)
CC @hwchase17 @baskaryan
3 months ago
Mr. Lance E Sloan «UMich» 84dc2dd059
community[patch]: Load YouTube transcripts (captions) as fixed-duration chunks with start times (#21710)
- **Description:** Add a new format, `CHUNKS`, to
`langchain_community.document_loaders.youtube.YoutubeLoader` which
creates multiple `Document` objects from YouTube video transcripts
(captions), each of a fixed duration. The metadata of each chunk
`Document` includes the start time of each one and a URL to that time in
the video on the YouTube website.
  
I had implemented this for UMich (@umich-its-ai) in a local module, but
it makes sense to contribute this to LangChain community for all to
benefit and to simplify maintenance.

- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter:** lsloan_umich
- **Mastodon:**
[lsloan@mastodon.social](https://mastodon.social/@lsloan)

With regards to **tests and documentation**, most existing features of
the `YoutubeLoader` class are not tested. Only the
`YoutubeLoader.extract_video_id()` static method had a test. However,
while I was waiting for this PR to be reviewed and merged, I had time to
add a test for the chunking feature I've proposed in this PR.

I have added an example of using chunking to the
`docs/docs/integrations/document_loaders/youtube_transcript.ipynb`
notebook.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
3 months ago
Aayush Kataria 71811e0547
community[minor]: Adds a vector store for Azure Cosmos DB for NoSQL (#21676)
This PR add supports for Azure Cosmos DB for NoSQL vector store.

Summary:

Description: added vector store integration for Azure Cosmos DB for
NoSQL Vector Store,
Dependencies: azure-cosmos dependency,
Tag maintainer: @hwchase17, @baskaryan @efriis @eyurtsev

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
3 months ago
Mohammad Mohtashim 36cad5d25c
[Community]: Added Metadata filter support for DocumentDB Vector Store (#22777)
- **Description:** As pointed out in this issue #22770, DocumentDB
`similarity_search` does not support filtering through metadata which
this PR adds by passing in the parameter `filter`. Also this PR fixes a
minor Documentation error.
- **Issue:** #22770

---------

Co-authored-by: Erick Friis <erickfriis@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
3 months ago
Dmitry Stepanov 912751e268
Ollama vision support (#22734)
**Description:** Ollama vision with messages in OpenAI-style support `{
"image_url": { "url": ... } }`
**Issue:** #22460 

Added flexible solution for ChatOllama to support chat messages with
images. Works when you provide either `image_url` as a string or as a
dict with "url" inside (like OpenAI does). So it makes available to use
tuples with `ChatPromptTemplate.from_messages()`

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
3 months ago
Philippe PRADOS 0908b01cb2
langchain[minor]: Add native async implementation to LLMFilter, add concurrency to both sync and async paths (#22739)
Thank you for contributing to LangChain!

- [ ] **PR title**: "langchain: Fix chain_filter.py to be compatible
with async"


- [ ] **PR message**: 
    - **Description:** chain_filter is not compatible with async.
    - **Twitter handle:** pprados


- [X ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

---------

Signed-off-by: zhangwangda <zhangwangda94@163.com>
Co-authored-by: Prakul <discover.prakul@gmail.com>
Co-authored-by: Lei Zhang <zhanglei@apache.org>
Co-authored-by: Gin <ictgtvt@gmail.com>
Co-authored-by: wangda <38549158+daziz@users.noreply.github.com>
Co-authored-by: Max Mulatz <klappradla@posteo.net>
3 months ago
Jaeyeon Kim(김재연) ce4e29ae42
community[minor]: fix redis store docstring and streamline initialization code (#22730)
Thank you for contributing to LangChain!

### Description

Fix the example in the docstring of redis store.
Change the initilization logic and remove redundant check, enhance error
message.

### Issue

The example in docstring of how to use redis store was wrong.

![image](https://github.com/langchain-ai/langchain/assets/37469330/78c5d9ce-ee66-45b3-8dfe-ea29f125e6e9)

### Dependencies
Nothing



- [ ] **Add tests and docs**: 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/docs/integrations` directory.


- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
3 months ago
am-kinetica ad101adec8
community[patch]: Kinetica Integrations handled error in querying; quotes in table names; updated gpudb API (#22724)
- [ ] **Miscellaneous updates and fixes**: 
- **Description:** Handled error in querying; quotes in table names;
updated gpudb API
- **Issue:** Threw an error with an error message difficult to
understand if a query failed or returned no records
    - **Dependencies:** Updated GPUDB API version to `7.2.0.9`


@baskaryan @hwchase17
3 months ago
NithinBairapaka 27b9ea14a5
docs: Updated integration docs with required package installations (#22392)
**Title:** Updated integration docs with required package installations
   **Issue:**  #22005
3 months ago
Albert Gil López 1710423de3
docs: correct path in readme (#22383)
Description: Fix incorrect path in README instructions.
Issue: N/A
Dependencies: None
Twitter handle: @jddam

---------

Co-authored-by: isaac hershenson <ihershenson@hmc.edu>
3 months ago
Greg Tracy 7e115da16c
docs: Fix pixelation in stack graphic (#21554)
This change updates the stack graphic displayed in the top-level README.
The LangChain tile is pixelated in the current graphic.
3 months ago