Commit Graph

11218 Commits (0c69c9fb3f1870a0dc8eb17fa0ed600dec1e22e2)
 

Author SHA1 Message Date
Swastik-Swarup-Dash 6247259438
update_readme (#25665)
Updated LangChain Expression Language (LCEL). for Easier Understanding
4 weeks ago
Noah Mayerhofer 0091947efd
community: add retry for session expired exception in neo4j (#25660)
Description: The neo4j driver can raise a SessionExpired error, which is
considered a retriable error. If a query fails with a SessionExpired
error, this change retries every query once. This change will make the
neo4j integration less flaky.
Twitter handle: noahmay_
4 weeks ago
Erick Friis e958f76160
docs: migration guide nits (#25600) 4 weeks ago
Yuki Watanabe 3981d736df
databricks: Add partner package directory and ChatDatabricks implementation (#25430)
### Summary

Create `langchain-databricks` as a new partner packages. This PR does
not migrate all existing Databricks integration, but the package will
eventually contain:

* `ChatDatabricks` (implemented in this PR)
* `DatabricksVectorSearch`
* `DatabricksEmbeddings`
* ~`UCFunctionToolkit`~ (will be done after UC SDK work which
drastically simplify implementation)

Also, this PR does not add integration tests yet. This will be added
once the Databricks test workspace is ready.

Tagging @efriis as POC


### Tracker
[✍️] Create a package and imgrate ChatDatabricks
[ ] Migrate DatabricksVectorSearch, DatabricksEmbeddings, and their docs
~[ ] Migrate UCFunctionToolkit and its doc~
[ ] Add provider document and update README.md
[ ] Add integration tests and set up secrets (after moved to an external
package)
[ ] Add deprecation note to the community implementations.

---------

Signed-off-by: B-Step62 <yuki.watanabe@databricks.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
4 weeks ago
Scott Hurrey fb1d67edf6
box: add retrievers and fix docs (#25633)
Thank you for contributing to LangChain!


**Description:** Adding `BoxRetriever` for langchain_box. This retriever
handles two use cases:
* Retrieve all documents that match a full-text search
* Retrieve the answer to a Box AI prompt as a Document

**Twitter handle:** @BoxPlatform


- [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: Erick Friis <erick@langchain.dev>
4 weeks ago
Bagatur 4f347cbcb9
docs: link Versions in intro (#25640) 4 weeks ago
jakerachleff 4591bc0b01
Use 1.101 instead of 1.100 bc 1.100 was yanked (#25638) 4 weeks ago
Bagatur f535e8a99e
docs: ls similar examples header (#25642) 4 weeks ago
Erick Friis 766b650fdc
chroma: add back fastapi optional dep (#25641) 4 weeks ago
Bagatur 9daff60698
docs: fix openai api ref (#25639) 4 weeks ago
Erick Friis c8be0a9f70
partners/unstructured: release 0.1.2 (#25637) 4 weeks ago
Bagatur f4b3c90886
docs: add prereq commas (#25626) 4 weeks ago
Christophe Bornet b71ae52e65
[unstructured][security] Bump unstructured version (#25364)
This ensures version 0.15.7+ is pulled. 
This version of unstructured uses a version of NLTK >= 3.8.2 that has a
fix for a critical CVE:
https://github.com/advisories/GHSA-cgvx-9447-vcch
4 weeks ago
Bagatur 39c44817ae
infra: test convert_message (#25632) 4 weeks ago
Bagatur 4feda41ab6
docs: ls how to link (#25624) 4 weeks ago
Bagatur 71c2ec6782
docs: langsmith few shot prereq (#25623) 4 weeks ago
Bagatur 628574b9c2
core[patch]: Release 0.2.34 (#25622) 4 weeks ago
Bagatur 0bc3845e1e
core[patch]: support oai dicts as messages (#25621)
and update langsmtih example selector docs
4 weeks ago
Bagatur a78843bb77
docs: how to use langsmith few shot (#25601)
Requires langsmith 0.1.101 release
1 month ago
ccurme 10a2ce2a26
together[patch]: use mixtral in standard integration tests (#25619)
Mistral 7B occasionally fails tool-calling tests. Updating to Mixtral
appears to improve this.
1 month ago
Mikhail Khludnev d457d7d121
docs: Update qdrant.ipynb "BM25".lower() (#25616)
Otherwise I've got KeyError from `fastembeds`
1 month ago
Dristy Srivastava b002702af6
[Community][minor]: Updating metadata with full_path in SharePoint loader (#25593)
- **Description:** Updating metadata for sharepoint loader with full
path i.e., webUrl
- **Issue:** NA
- **Dependencies:** NA
- **Tests:** NA
- **Docs** NA

Co-authored-by: dristy.cd <dristy@clouddefense.io>
Co-authored-by: ccurme <chester.curme@gmail.com>
1 month ago
ZhangShenao 34d0417eb5
Improvement[Doc] Improve api doc in of `PineconeVectorStore` (#25605)
Complete missing arguments in api doc of `PineconeVectorStore`.
1 month ago
wangda e7d6b25653
docs:Correcting spelling mistakes (#25612) 1 month ago
Scott Hurrey 55fd2e2158
box: add langchain box package and DocumentLoader (#25506)
Thank you for contributing to LangChain!

-Description: Adding new package: `langchain-box`:

* `langchain_box.document_loaders.BoxLoader` — DocumentLoader
functionality
* `langchain_box.utilities.BoxAPIWrapper` — Box-specific code
* `langchain_box.utilities.BoxAuth` — Helper class for Box
authentication
* `langchain_box.utilities.BoxAuthType` — enum used by BoxAuth class

- Twitter handle: @boxplatform


- [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: Erick Friis <erickfriis@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
1 month ago
Bagatur be27e1787f
docs: few-shot conceptual guide (#25596)
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: jakerachleff <jake@langchain.dev>
1 month ago
Erick Friis f878df404f
partners/chroma: release 0.1.3 (#25599) 1 month ago
Erick Friis 60cf49a618
chroma: ban chromadb sdk versions 0.5.4 and 0.5.5 due to pydantic bug (#25586)
also remove some unused dependencies (fastapi) and unused test/lint/dev
dependencies (community, openai, textsplitters)

chromadb 0.5.4 introduced usage of `model_fields` which is pydantic v2
specific. also released in 0.5.5
1 month ago
Erick Friis e37caa9b9a
core: fix fallback context overwriting (#25550)
fixes #25337
1 month ago
Bagatur 3e296e39c8
docs: update examples in api ref (#25589) 1 month ago
Isaac Francisco d40bdd6257
docs: more indexing of document loaders (#25500)
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
1 month ago
Bagatur 8a71f1b41b
core[minor]: add langsmith document loader (#25493)
needs tests
1 month ago
Bob Merkus 8e3e532e7d
docs: ollama doc update (toolcalling, install, notebook examples) (#25549)
The new `langchain-ollama` package seems pretty well implemented, but I
noticed the docs were still outdated so I decided to fix em up a bit.

- Llama3.1 was release on 23rd of July;
https://ai.meta.com/blog/meta-llama-3-1/
- Ollama supports tool calling since 25th of July;
https://ollama.com/blog/tool-support
- LangChain Ollama partner package was released 1st of august;
https://pypi.org/project/langchain-ollama/

**Problem**: Docs note langchain-community instead of langchain-ollama

**Solution**: Update docs to
https://python.langchain.com/v0.2/docs/integrations/chat/ollama/


**Problem**: OllamaFunctions is deprecated, as noted on
[Integrations](https://python.langchain.com/v0.2/docs/integrations/chat/ollama_functions/):
This was an experimental wrapper that attempts to bolt-on tool calling
support to models that do not natively support it. The [primary Ollama
integration](https://python.langchain.com/v0.2/docs/integrations/chat/ollama/) now
supports tool calling, and should be used instead.

**Solution**: Delete old notebook from repo, update the existing one
with @tool decorator + pydantic examples to the notebook


**Problem**: Llama3.1 was released while llama3-groq-tool-call fine-tune
Is noted in notebooks.

**Solution**: update docs + notebooks to llama3.1 (which has improved
tool calling support)


**Problem**: Install instructions are incomplete, there is no
information to download a model and/or run the Ollama server

**Solution**: Add simple instructions to start the ollama service and
pull model (for toolcalling)

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
1 month ago
Jabir 12e490ea56
Update azuresearch.py (#25577)
This will allow complextype metadata to be returned. the current
implementation throws error when dealing with nested metadata

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"


- [ ] **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.

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
1 month ago
Abraham Omorogbe 498a482e76
docs: Adding Azure Database for PostgreSQL docs (#25560)
This PR to show support for the Azure Database for PostgreSQL Vector
Store and Memory

[Azure Database for PostgreSQL - Flexible
Server](https://learn.microsoft.com/en-us/azure/postgresql/flexible-server/service-overview)
[Azure Database for PostgreSQL pgvector
extension](https://learn.microsoft.com/en-us/azure/postgresql/flexible-server/how-to-use-pgvector)

**Description:** Added vector store and memory usage documentation for
Azure Database for PostgreSQL
 **Twitter handle:** [@_aiabe](https://x.com/_aiabe)

---------

Co-authored-by: Abeomor <{ID}+{username}@users.noreply.github.com>
1 month ago
Leonid Ganeline d324fd1821
docs: added Constitutional AI references (#25553)
Added reference to the source paper.
1 month ago
Bagatur 4bd005adb6
core[patch]: Allow bound models as token_counter in trim_messages (#25563) 1 month ago
Erick Friis e01c6789c4
core,community: add beta decorator to missed GraphVectorStore extensions (#25562) 1 month ago
Erick Friis dd2d094adc
infra: remove huggingface from ci tree (#25559) 1 month ago
Bagatur 6b98207eda
infra: test chat prompt ser/des (#25557) 1 month ago
ccurme c5bf114c0f
together, standard-tests: specify tool_choice in standard tests (#25548)
Here we allow standard tests to specify a value for `tool_choice` via a
`tool_choice_value` property, which defaults to None.

Chat models [available in
Together](https://docs.together.ai/docs/chat-models) have issues passing
standard tool calling tests:
- llama 3.1 models currently [appear to rely on user-side
parsing](https://docs.together.ai/docs/llama-3-function-calling) in
Together;
- Mixtral-8x7B and Mistral-7B (currently tested) consistently do not
call tools in some tests.

Specifying tool_choice also lets us remove an existing `xfail` and use a
smaller model in Groq tests.
1 month ago
maang-h 015ab91b83
community[patch]: Add ToolMessage for ChatZhipuAI (#25547)
- **Description:** Add ToolMessage for `ChatZhipuAI` to solve the issue
#25490
1 month ago
ccurme 5a3aaae6dc
groq[patch]: update model used for llama tests (#25542)
`llama-3.1-8b-instant` often fails some of the tool calling standard
tests. Here we update to `llama-3.1-70b-versatile`.
1 month ago
Mohammad Mohtashim 75c3c81b8c
[Community]: Fix - Open AI Whisper `client.audio.transcriptions` returning Text Object which raises error (#25271)
- **Description:** The following
[line](fd546196ef/libs/community/langchain_community/document_loaders/parsers/audio.py (L117))
in `OpenAIWhisperParser` returns a text object for some odd reason
despite the official documentation saying it should return `Transcript`
Instance which should have the text attribute. But for the example given
in the issue and even when I tried running on my own, I was directly
getting the text. The small PR accounts for that.
 - **Issue:** : #25218
 

I was able to replicate the error even without the GenericLoader as
shown below and the issue was with `OpenAIWhisperParser`

```python
parser = OpenAIWhisperParser(api_key="sk-fxxxxxxxxx",
                                            response_format="srt",
                                            temperature=0)

list(parser.lazy_parse(Blob.from_path('path_to_file.m4a')))
```
1 month ago
Thin red line 未来产品经理 0f7b8adddf
fix issue: cannot use document_variable_name to override context in create_stuff_documents_chain (#25531)
…he prompt in the create_stuff_documents_chain

Thank you for contributing to LangChain!

- [ ] **PR title**: "langchain:add document_variable_name in the
function _validate_prompt in create_stuff_documents_chain"
 

- [ ] **PR message**: 
- **Description:** add document_variable_name in the function
_validate_prompt in create_stuff_documents_chain
- **Issue:** according to the description of
create_stuff_documents_chain function, the parameter
document_variable_name can be used to override the "context" in the
prompt, but in the function, _validate_prompt it still use DOCUMENTS_KEY
to check if it is a valid prompt, the value of DOCUMENTS_KEY is always
"context", so even through the user use document_variable_name to
override it, the code still tries to check if "context" is in the
prompt, and finally it reports error. so I use document_variable_name to
replace DOCUMENTS_KEY, the default value of document_variable_name is
"context" which is same as DOCUMENTS_KEY, but it can be override by
users.
    - **Dependencies:** none
    - **Twitter handle:** https://x.com/xjr199703


- [ ] **Add tests and docs**: none

- [ ] **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: Chester Curme <chester.curme@gmail.com>
1 month ago
ccurme 09c0823c3a
docs: update summarization guides (#25408) 1 month ago
maang-h 32f5147523
docs: Fix QianfanLLMEndpoint and Tongyi input text (#25529)
- **Description:** Fix `QianfanLLMEndpoint` and `Tongyi` input text.
1 month ago
ZhangShenao 4255a30f20
Improvement[Community] Improve api doc for `SingleFileFacebookMessengerChatLoader` (#25536)
Delete redundant args in api doc
1 month ago
Bagatur 49dea06af1
docs: fix Agent deprecation msg (#25464) 1 month ago
Hassan El Mghari 937b3904eb
together[patch]: update base url (#25524)
Updated the Together base URL from `.ai` to `.xyz` since some customers
have reported problems with `.ai`.
1 month ago