Commit Graph

6951 Commits

Author SHA1 Message Date
William FH
129552e3d6
Rm deprecated (#15920)
Remove the usage of deprecated methods in the test runner.
2024-01-11 18:10:49 -08:00
Nuno Campos
438beb6c94
Pass config specs through ensemble retriever (#15917)
<!-- 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.
 -->

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2024-01-11 16:22:17 -08:00
Erick Friis
ebb6ad4f7a
mistralai[patch]: release 0.0.2 (#15912) 2024-01-11 13:42:04 -08:00
Erick Friis
437cebc955
core[patch]: release 0.1.10 (#15911) 2024-01-11 13:39:06 -08:00
Harrison Chase
80d41a8da3
add old serializable mapping (#15906) 2024-01-11 13:03:12 -08:00
Erick Friis
623f87c888
community[patch]: pinecone bug (#15905) 2024-01-11 11:44:07 -08:00
Eugene Yurtsev
44101b6b0e
Docs[patch]: Update OpenAI tools agent description (#15896)
Update OpenAI tools agent description.
2024-01-11 14:39:11 -05:00
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
2024-01-11 14:38:48 -05:00
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
2024-01-11 10:24:15 -08:00
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
2024-01-11 07:52:29 -08:00
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.
 -->
2024-01-10 20:30:44 -08:00
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
2024-01-10 20:29:01 -08:00
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>
2024-01-10 19:33:10 -08:00
Harrison Chase
97411e998f
[docs] add beautiful soup dependency (#15860) 2024-01-10 19:32:55 -08:00
Daniel
6d299a55c0
docs: Update cohere.mdx, Text embedding had incorrect code snippet (#15840)
text embedding code snippet was incorrect.
2024-01-10 19:25:29 -08:00
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>
2024-01-10 18:39:16 -08:00
Erick Friis
38523d7c57
together[minor]: add llm (#15853) 2024-01-10 17:55:34 -08:00
William FH
2895ca87cf
Update Evals Notebook (#15851) 2024-01-10 16:33:34 -08:00
Erick Friis
ee708739c3
community[patch]: pinecone v3 support (#15849)
Info in slack

---------

Co-authored-by: Roie Schwaber-Cohen <roie.cohen@gmail.com>
2024-01-10 14:54:50 -08:00
Bagatur
18411c379c
docs: fix links (#15848) 2024-01-10 17:39:06 -05:00
Lance Martin
9c871f427b
TogetherAI RAG (#15846) 2024-01-10 14:28:05 -08:00
Eugene Yurtsev
a06db53c37
Add unit tests to test openai tools agent (#15843)
This PR adds unit testing to test openai tools agent.
2024-01-10 17:06:30 -05:00
Harrison Chase
21a1538949
add raga reranker (#15838) 2024-01-10 11:07:19 -08:00
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.
2024-01-10 13:27:07 -05:00
Eugene Yurtsev
c425e6f740
More updates to issue template (#15833)
More update to issue template
2024-01-10 13:16:02 -05:00
Eugene Yurtsev
65980c22b8
Infra: Fix syntax error in BUG REPORT template (#15831)
Fix syntax error in issue template
2024-01-10 12:39:08 -05:00
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>
2024-01-10 12:35:41 -05:00
Bagatur
6432494f9d
infra: explicitly specify py path (#15826) 2024-01-10 11:59:43 -05:00
Bagatur
79124fd71d
experimental[patch]: Release 0.0.49 (#15823) 2024-01-10 11:23:19 -05:00
Harrison Chase
20abe24819
experimental[minor]: Add semantic chunker (#15799) 2024-01-10 11:18:30 -05:00
Harrison Chase
a1d7f2b3e1
add dspy notebook (#15798) 2024-01-10 08:01:08 -08:00
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)
2024-01-10 10:53:01 -05:00
Erick Friis
85a4594ed7
community[patch]: more deprecations (#15782) 2024-01-09 20:36:16 -08:00
Erick Friis
33dccf0f66
core[patch]: release 0.1.9 (#15794) 2024-01-09 19:27:19 -08:00
Bagatur
942071bf57
docs: collapse structured use case (#15791) 2024-01-09 21:47:09 -05:00
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>
2024-01-09 16:27:20 -08:00
Erick Friis
323941a90a
mistralai[patch]: persist async client (#15786) 2024-01-09 16:21:39 -08:00
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>
2024-01-09 15:33:44 -08:00
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>
2024-01-09 15:29:25 -08:00
Erick Friis
656e87beb9
core[patch]: add alternative_import to deprecated (#15781) 2024-01-09 14:45:28 -08:00
Erick Friis
04a5a37e92
robocorp[patch]: fix readme, release 0.0.1.post1 (#15777) 2024-01-09 12:53:57 -08:00
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>
2024-01-09 12:41:20 -08:00
Erick Friis
91ec9da534
openai[patch]: unit test load (#15624) 2024-01-09 11:54:11 -08:00
Erick Friis
7be72e1103
openai[patch], docs: readme (#15773) 2024-01-09 11:52:24 -08:00
Bagatur
ee5bd986de
community[patch]: update oai deprecation message (#15681)
addresses #15674
2024-01-09 14:36:58 -05:00
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>
2024-01-09 11:29:19 -08:00
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
2024-01-09 11:13:10 -08:00
Bagatur
1b0db82dbe
docs: fix recognition (#15769) 2024-01-09 13:57:28 -05:00
Erick Friis
4ed3d17c47
community[patch]: release 0.0.11 (#15760) 2024-01-09 09:44:26 -08:00
Bagatur
da395f3182
experimental[patch]: loosen core max version (#15763) 2024-01-09 12:10:14 -05:00