Commit Graph

6844 Commits (46b7a8d913ab77c76bf9646d8347c2f6547896f5)
 

Author SHA1 Message Date
Eugene Yurtsev 46b7a8d913
Docs[patch]: Update agent quick start for agents (#15892)
Minor change:

1) Update tool invocation to use .invoke
2) Show hub prompt
8 months ago
Jacob Lee c11dbefedc
docs[patch]: Fix bad headers in output parser docs (#15778)
Currently looks like this:

<img width="282" alt="Screenshot 2024-01-09 at 1 08 53 PM"
src="https://github.com/langchain-ai/langchain/assets/6952323/58f3d368-6588-418e-8502-30d13757cb99">

CC @efriis @baskaryan
8 months ago
Christophe Bornet c56060bb7d
Add document loader section to Astra provider doc page (#15882)
See preview:
https://langchain-git-fork-cbornet-provider-astra-doc-loader-langchain.vercel.app/docs/integrations/providers/astradb#ocument-loader
8 months ago
xvjixiang 611f18c944
Docs: Fix a typo in elasticsearch vectorstore notebook (#15807)
<!-- Thank you for contributing to LangChain!

Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.

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,
- **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` from the root
of the package you've modified to check this locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/

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.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
8 months ago
axiangcoding d5aa277b94
community: add collection_properties parameter to Milvus (#15788)
- **Description:** add collection_properties parameter to Milvus. See
[pymilvus set_properties()
description](https://milvus.io/api-reference/pymilvus/v2.3.x/Collection/set_properties().md)
  - **Issue:** None
  - **Dependencies:** None
  - **Twitter handle:** None
8 months ago
mogith-pn 9e1ed17bfb
Community : Modified doc strings and example notebook for Clarifai (#15816)
Community : Modified doc strings and example notebook for Clarifai

Description:
1. Modified doc strings inside clarifai vectorstore class and
embeddings.
2. Modified notebook examples.

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
8 months ago
Harrison Chase 97411e998f
[docs] add beautiful soup dependency (#15860) 8 months ago
Daniel 6d299a55c0
docs: Update cohere.mdx, Text embedding had incorrect code snippet (#15840)
text embedding code snippet was incorrect.
8 months ago
Sagar B Manjunath e6240fecab
templates: Add NVIDIA Canonical RAG example chain (#15758)
- **Description:** Adds a RAG template that uses NVIDIA AI playground
and embedding models, along with Milvus vector store

- **Dependencies:** This template depends on the AI playground service
in NVIDIA NGC. API keys with a significant trial compute are available
(10k queries at the time of writing). This template also depends on the
Milvus Vector store which is publicly available.

Note: [A quick link to get a
key](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/ai-foundation/models/codellama-13b/api)
when you have an NGC account. Generate Key button at the top right of
the code window.

---------

Co-authored-by: Sagar B Manjunath <sbogadimanju@nvidia.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
8 months ago
Erick Friis 38523d7c57
together[minor]: add llm (#15853) 8 months ago
William FH 2895ca87cf
Update Evals Notebook (#15851) 8 months ago
Erick Friis ee708739c3
community[patch]: pinecone v3 support (#15849)
Info in slack

---------

Co-authored-by: Roie Schwaber-Cohen <roie.cohen@gmail.com>
8 months ago
Bagatur 18411c379c
docs: fix links (#15848) 8 months ago
Lance Martin 9c871f427b
TogetherAI RAG (#15846) 8 months ago
Eugene Yurtsev a06db53c37
Add unit tests to test openai tools agent (#15843)
This PR adds unit testing to test openai tools agent.
8 months ago
Harrison Chase 21a1538949
add raga reranker (#15838) 8 months ago
Eugene Yurtsev 45f49ca439
infra: fix issue preview (#15836)
Fixing the placeholder for the code example. GitHub collapses newlines
when
trying to use the text area, which is super confusing.
8 months ago
Eugene Yurtsev c425e6f740
More updates to issue template (#15833)
More update to issue template
8 months ago
Eugene Yurtsev 65980c22b8
Infra: Fix syntax error in BUG REPORT template (#15831)
Fix syntax error in issue template
8 months ago
Eugene Yurtsev e182d630f7
ISSUE_TEMPLATE: Update issue template (#15757)
Drop some fields, re-order, start directing folks towards QA.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
8 months ago
Bagatur 6432494f9d
infra: explicitly specify py path (#15826) 8 months ago
Bagatur 79124fd71d
experimental[patch]: Release 0.0.49 (#15823) 8 months ago
Harrison Chase 20abe24819
experimental[minor]: Add semantic chunker (#15799) 8 months ago
Harrison Chase a1d7f2b3e1
add dspy notebook (#15798) 8 months ago
Eugene Yurtsev feb41c5e28
langchain[patch]: Improve stream_log with AgentExecutor and Runnable Agent (#15792)
This PR fixes an issue where AgentExecutor with RunnableAgent does not allow users to see individual llm tokens if streaming=True is not set explicitly on the underlying chat model.

The majority of this PR is testing code:

1. Create a test chat model that makes it easier to test streaming and
supports AIMessages that include function invocation information.
2. Tests for the chat model
3. Tests for RunnableAgent (previously untested)
4. Tests for openai agent (previously untested)
8 months ago
Erick Friis 85a4594ed7
community[patch]: more deprecations (#15782) 8 months ago
Erick Friis 33dccf0f66
core[patch]: release 0.1.9 (#15794) 8 months ago
Bagatur 942071bf57
docs: collapse structured use case (#15791) 8 months ago
Erick Friis 0c95f3a981
mistralai[patch]: warn on stop token, fix on_llm_new_token (#15787)
Fixes #15269

Addresses with warning. MistralAI API doesn't support stop token yet.

---------

Co-authored-by: Niels Garve <info@nielsgarve.com>
8 months ago
Erick Friis 323941a90a
mistralai[patch]: persist async client (#15786) 8 months ago
Tomaz Bratanic 3e0cd11f51
templates: Add neo4j semantic layer template (#15652)
Co-authored-by: Tomaz Bratanic <tomazbratanic@Tomazs-MacBook-Pro.local>
Co-authored-by: Erick Friis <erick@langchain.dev>
8 months ago
NuODaniel 70b6315b23
community[patch]: fix qianfan chat stream calling caused exception (#13800)
- **Description:** 
`QianfanChatEndpoint` extends `BaseChatModel` as a super class, which
has a default stream implement might concat the MessageChunk with
`__add__`. When call stream(), a ValueError for duplicated key will be
raise.
  - **Issues:** 
     * #13546  
     * #13548
     * merge two single test file related to qianfan.
  - **Dependencies:** no
  - **Tag maintainer:**

---------

Co-authored-by: root <liujun45@baidu.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
8 months ago
Erick Friis 656e87beb9
core[patch]: add alternative_import to deprecated (#15781) 8 months ago
Erick Friis 04a5a37e92
robocorp[patch]: fix readme, release 0.0.1.post1 (#15777) 8 months ago
Erick Friis ae67ba4dbb
templates: robocorp action server template (#15776)
---------

Co-authored-by: Rihards Gravis <rihards@gravis.lv>
Co-authored-by: Mikko Korpela <mikko@robocorp.com>
8 months ago
Erick Friis 91ec9da534
openai[patch]: unit test load (#15624) 8 months ago
Erick Friis 7be72e1103
openai[patch], docs: readme (#15773) 8 months ago
Bagatur ee5bd986de
community[patch]: update oai deprecation message (#15681)
addresses #15674
8 months ago
Erick Friis 7562f70c95
robocorp[minor]: Add robocorp action server toolkit (#15766)
Co-authored-by: Rihards Gravis <rihards@gravis.lv>
Co-authored-by: Mikko Korpela <mikko@robocorp.com>
8 months ago
Erick Friis 7bc100fd43
docs: integration package pip installs (#15762)
More than 300 files - will fail check_diff. Will merge after Vercel
deploy succeeds

Still occurrences that need changing - will update more later
8 months ago
Bagatur 1b0db82dbe
docs: fix recognition (#15769) 8 months ago
Erick Friis 4ed3d17c47
community[patch]: release 0.0.11 (#15760) 8 months ago
Bagatur da395f3182
experimental[patch]: loosen core max version (#15763) 8 months ago
Shoya SHIRAKI 123e01b9d8
docs: remove unnecessary description (#15752)
| before | after |
| ---- | ---- |
|
![image](https://github.com/langchain-ai/langchain/assets/1635118/c108c53c-2665-46c3-82bf-8f74005f9ac9)
|
![image](https://github.com/langchain-ai/langchain/assets/1635118/2da3427a-1bac-4e9e-9fb2-509c9674d8a1)
|

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
8 months ago
Eugene Yurtsev 7db680fd4b
CI: Fix template for questions (#15756)
CI: Workflow fix template for questions
8 months ago
Eugene Yurtsev ce68be67ad
Update template to direct questions to discussions rather than issues (#15721)
Update PR template to direct questions to discussions rather than issues
8 months ago
William FH 04caf07dee
Make packages optional (#15727)
So we don't have to instruct people to modify the Dockerfile every time
they delete the packages directory.


See:
https://stackoverflow.com/questions/70096208/dockerfile-copy-folder-if-it-exists-conditional-copy/70096420#70096420

Tested on a new repo
8 months ago
Eugene Yurtsev 3a8ad90509
langchain(patch): Fix output type for pydantic output parser (#15714)
This PR fixes the output type for the pydantic output parser.

Fix for: https://github.com/langchain-ai/langserve/issues/301
8 months ago
Erick Friis 95a2c92e26
experimental[patch]: minimum version bump (#15724)
- experimental: minimum version bump
- actually 0.1.5
- actually 0.1.7
8 months ago
Erick Friis 6c9b7c2cec
experimental: minimum version bump (#15722)
experimental relies on `from langchain_core.runnables.config import
run_in_executor` which was introduced in core 0.1.5.

Updated pyproject dependency as well as minimum version test.
8 months ago