github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-01 11:02:37 +00:00
Code Issues Packages Projects Releases Wiki Activity
13,111 Commits 976 Branches 960 Tags
5fb261ce277eebc473bcf50b2bc189a06d4fd811
Commit Graph

13111 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Bagatur
60123bef67 docs: fix trim_messages docstring (#27948) 2024-11-06 22:25:13 +00:00
murrlincoln
14f1827953 docs: Adding notebook for cdp agentkit toolkit (#27910) 
- **Description:** Adding in the first pass of documentation for the CDP
Agentkit Toolkit
    - **Issue:** N/a
    - **Dependencies:** cdp-langchain
    - **Twitter handle:** @CoinbaseDev

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: John Peterson <john.peterson@coinbase.com>
 2024-11-06 13:28:27 -08:00
Eric Pinzur
ea0ad917b0 community: added Document.id support to opensearch vectorstore (#27945) 
Description:
* Added support of Document.id on OpenSearch vector store
* Added tests cases to match
 2024-11-06 15:04:09 -05:00
Hammad Randhawa
75aa82fedc docs: Completed sentence under the heading "Instantiating a Browser … (#27944) 
…Toolkit" in "playwright.ipynb" integration.

- Completed the incomplete sentence in the Langchain Playwright
documentation.

- Enhanced documentation clarity to guide users on best practices for
instantiating browser instances with Langchain Playwright.

Example before:
> "It's always recommended to instantiate using the from_browser method
so that the

Example after:
> "It's always recommended to instantiate using the `from_browser`
method so that the browser context is properly initialized and managed,
ensuring seamless interaction and resource optimization."

Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-06 19:55:00 +00:00
Bagatur
67ce05a0a7 core[patch]: make oai tool description optional (#27756) 2024-11-06 18:06:47 +00:00
Bagatur
b2da3115ed docs: document init_chat_model standard params (#27812) 2024-11-06 09:50:07 -08:00
Dobiichi-Origami
395674d503 community: re-arrange function call message parse logic for Qianfan (#27935) 
the [PR](https://github.com/langchain-ai/langchain/pull/26208) two month
ago has a potential bug which causes malfunction of `tool_call` for
`QianfanChatEndpoint` waiting for fix
 2024-11-06 09:58:16 -05:00
Erick Friis
41b7a5169d infra: starter codeowners file (#27929) 2024-11-05 16:43:11 -08:00
ccurme
66966a6e72 openai[patch]: release 0.2.6 (#27924) 
Some additions in support of [predicted
outputs](https://platform.openai.com/docs/guides/latency-optimization#use-predicted-outputs)
feature:
- Bump openai sdk version
- Add integration test
- Add example to integration docs

The `prediction` kwarg is already plumbed through model invocation.
langchain-openai==0.2.6 		2024-11-05 23:02:24 +00:00
Erick Friis
a8c473e114 standard-tests: ci pipeline (#27923) 2024-11-05 20:55:38 +00:00
Erick Friis
c3b75560dc infra: release note grep order of operations (#27922) langchain-qdrant==0.2.0 2024-11-05 12:44:36 -08:00
Erick Friis
b3c81356ca infra: release note compute 2 (#27921) langchain-nomic==0.1.4 2024-11-05 12:04:41 -08:00
Erick Friis
bff2a8b772 standard-tests: add tools standard tests (#27899) 2024-11-05 11:44:34 -08:00
SHJUN
f6b2f82099 community: chroma error patch(attribute changed on chroma) (#27827) 
There was a change of attribute name which was "max_batch_size". It's
now "get_max_batch_size" method.
I want to use "create_batches" which is right down below.

Please check this PR link.
reference: https://github.com/chroma-core/chroma/pull/2305

---------

Signed-off-by: Prithvi Kannan <prithvi.kannan@databricks.com>
Co-authored-by: Prithvi Kannan <46332835+prithvikannan@users.noreply.github.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Jun Yamog <jkyamog@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: ono-hiroki <86904208+ono-hiroki@users.noreply.github.com>
Co-authored-by: Dobiichi-Origami <56953648+Dobiichi-Origami@users.noreply.github.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Co-authored-by: Duy Huynh <vndee.huynh@gmail.com>
Co-authored-by: Rashmi Pawar <168514198+raspawar@users.noreply.github.com>
Co-authored-by: sifatj <26035630+sifatj@users.noreply.github.com>
Co-authored-by: Eric Pinzur <2641606+epinzur@users.noreply.github.com>
Co-authored-by: Daniel Vu Dao <danielvdao@users.noreply.github.com>
Co-authored-by: Ofer Mendelevitch <ofermend@gmail.com>
Co-authored-by: Stéphane Philippart <wildagsx@gmail.com>
 2024-11-05 19:43:11 +00:00
Tomaz Bratanic
a3bbbe6a86 update llm graph transformer documentation (#27905) 2024-11-05 11:54:26 -05:00
Erick Friis
31f4fb790d standard-tests: release 0.3.0 (#27900) 2024-11-04 17:29:15 -08:00
Erick Friis
ba5cba04ff infra: get min versions (#27896) 2024-11-04 23:46:13 +00:00
Bagatur
6973f7214f docs: sidebar capitalization (#27894) 2024-11-04 22:09:32 +00:00
Stéphane Philippart
4b8cd7a09a community: ✨ Use new OVHcloud batch embedding (#26209) 
- **Description:** change to do the batch embedding server side and not
client side
- **Twitter handle:** @wildagsx

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
 2024-11-04 16:40:30 -05:00
Erick Friis
a54f390090 infra: fix prev tag output (#27892) 2024-11-04 12:46:23 -08:00
Erick Friis
75f80c2910 infra: fix prev tag condition (#27891) 2024-11-04 12:42:22 -08:00
Ofer Mendelevitch
d7c39e6dbb community: update Vectara integration (#27869) 
Thank you for contributing to LangChain!

- **Description:** Updated Vectara integration
- **Issue:** refresh on descriptions across all demos and added UDF
reranker
- **Dependencies:** None
- **Twitter handle:** @ofermend

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-04 20:40:39 +00:00
Erick Friis
14a71a6e77 infra: fix prev tag calculation (#27890) 2024-11-04 12:38:39 -08:00
Daniel Vu Dao
5745f3bf78 docs: Update messages.mdx (#27856) 
### Description
Updates phrasing for the header of the `Messages` section.

Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-04 20:36:31 +00:00
sifatj
e02a5ee03e docs: Update VectorStore as_retriever method url in qa_chat_history_how_to.ipynb (#27844) 
**Description**: Update VectorStore `as_retriever` method api reference
url in `qa_chat_history_how_to.ipynb`

Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-04 20:34:50 +00:00
sifatj
dd1711f3c2 docs: Update max_marginal_relevance_search api reference url in multi_vector.ipynb (#27843) 
**Description**: Update VectorStore `max_marginal_relevance_search` api
reference url in `multi_vector.ipynb`

Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-04 20:31:36 +00:00
sifatj
aa1f46a03a docs: Update VectorStore .as_retriever method url in vectorstore_retriever.ipynb (#27842) 
**Description**: Update VectorStore `.as_retriever` method url in
`vectorstore_retriever.ipynb`

Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-04 20:28:11 +00:00
Eric Pinzur
8eb38622a6 community: fixed bug in GraphVectorStoreRetriever (#27846) 
Description:

This fixes an issue that mistakenly created in
https://github.com/langchain-ai/langchain/pull/27253. The issue
currently exists only in `langchain-community==0.3.4`.

Test cases were added to prevent this issue in the future.

Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-04 20:27:17 +00:00
sifatj
eecf95df9b docs: Update VectorStore api reference url in rag.ipynb (#27841) 
**Description**: Update VectorStore api reference url in `rag.ipynb`

Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-04 20:27:03 +00:00
sifatj
50563400fb docs: Update broken vectorstore urls in retrievers.ipynb (#27838) 
**Description**: Update outdated `VectorStore` api reference urls in
`retrievers.ipynb`

Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-04 20:26:03 +00:00
Bagatur
dfa83531ad qdrant,nomic[minor]: bump core deps (#27849) 2024-11-04 20:19:50 +00:00
Erick Friis
4e5cc84d40 infra: release tag compute (#27836) 2024-11-04 12:16:51 -08:00
Rashmi Pawar
f86a09f82c Add nvidia as provider for embedding, llm (#27810) 
Documentation: Add NVIDIA as integration provider

cc: @mattf @dglogo

Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-11-04 19:45:51 +00:00
Erick Friis
0c62684ce1 Revert "infra: add neo4j to package list" (#27887) 
Reverts langchain-ai/langchain#27833

Wait for release
 2024-11-04 18:18:38 +00:00
Erick Friis
bcf499df16 infra: add neo4j to package list (#27833) 2024-11-04 09:24:04 -08:00
Duy Huynh
a487ec47f4 community: set default output_token_limit value for PowerBIToolkit to fix validation error (#26308) 
### Description:
This PR sets a default value of `output_token_limit = 4000` for the
`PowerBIToolkit` to fix the unintentionally validation error.

### Problem:
When attempting to run a code snippet from [Langchain's PowerBI toolkit
documentation](https://python.langchain.com/v0.1/docs/integrations/toolkits/powerbi/)
to interact with a `PowerBIDataset`, the following error occurs:

```
pydantic.v1.error_wrappers.ValidationError: 1 validation error for QueryPowerBITool
output_token_limit
  none is not an allowed value (type=type_error.none.not_allowed)
```

### Root Cause:
The issue arises because when creating a `QueryPowerBITool`, the
`output_token_limit` parameter is unintentionally set to `None`, which
is the current default for `PowerBIToolkit`. However, `QueryPowerBITool`
expects a default value of `4000` for `output_token_limit`. This
unintended override causes the error.


17659ca2cd/libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py (L63)

17659ca2cd/libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py (L72-L79)

17659ca2cd/libs/community/langchain_community/tools/powerbi/tool.py (L39)

### Solution:
To resolve this, the default value of `output_token_limit` is now
explicitly set to `4000` in `PowerBIToolkit` to prevent the accidental
assignment of `None`.

Co-authored-by: ccurme <chester.curme@gmail.com>
 2024-11-04 14:34:27 +00:00
Dobiichi-Origami
f7ced5b211 community: read function call from tool_calls for Qianfan (#26208) 
I added one more 'elif' to read tool call message from `tool_calls`

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
 2024-11-04 14:33:32 +00:00
ono-hiroki
b7d549ae88 docs: fix undefined 'data' variable in document_loader_csv.ipynb (#27872) 
**Description:** 
This PR addresses an issue in the CSVLoader example where data is not
defined, causing a NameError. The line `data = loader.load()` is added
to correctly assign the output of loader.load() to the data variable.
 2024-11-04 14:10:56 +00:00
Bagatur
3b0b7cfb74 chroma[minor]: release 0.2.0 (#27840) 2024-11-01 18:12:00 -07:00
Jun Yamog
830cad7bc0 core: fix CommaSeparatedListOutputParser to handle columns that may contain commas in it (#26365) 
- **Description:**
Currently CommaSeparatedListOutputParser can't handle strings that may
contain commas within a column. It would parse any commas as the
delimiter.
Ex. 
"foo, foo2", "bar", "baz"

It will create 4 columns: "foo", "foo2", "bar", "baz"

This should be 3 columns:

"foo, foo2", "bar", "baz"

- **Dependencies:**
Added 2 additional imports, but they are built in python packages.

import csv
from io import StringIO

- **Twitter handle:** @jkyamog

- [ ] **Add tests and docs**: 
1. added simple unit test test_multiple_items_with_comma

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
 2024-11-01 22:42:24 +00:00
Erick Friis
9fedb04dd3 docs: INVALID_CHAT_HISTORY redirect (#27845) 2024-11-01 21:35:11 +00:00
Erick Friis
03a3670a5e infra: remove some special cases (#27839) 2024-11-01 21:13:43 +00:00
Bagatur
002e1c9055 airbyte: remove from master (#27837) 2024-11-01 13:59:34 -07:00
Bagatur
ee63d21915 many: use core 0.3.15 (#27834) langchain-box==0.2.3 langchain-community==0.3.5 langchain-couchbase==0.2.2 langchain-exa==0.2.1 langchain-prompty==0.1.1 langchain-text-splitters==0.3.2 langchain-voyageai==0.1.3 langchain==0.3.7 2024-11-01 20:35:55 +00:00
Prithvi Kannan
c3c638cd7b docs: Reference new databricks-langchain package (#27828) 
Thank you for contributing to LangChain!

Update references in Databricks integration page to reference our new
partner package databricks-langchain
https://github.com/databricks/databricks-ai-bridge/tree/main/integrations/langchain

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.

---------

Signed-off-by: Prithvi Kannan <prithvi.kannan@databricks.com>
 2024-11-01 10:21:19 -07:00
sifatj
33d445550e docs: update VectorStore api reference url in retrievers.ipynb (#27814) 
**Description:** Update outdated `VectorStore` api reference url in
Vector store subsection of `retrievers.ipynb`
 2024-11-01 15:44:26 +00:00
sifatj
9a4a630e40 docs: Update Retrievers and Runnable links in Retrievers subsection of retrievers.ipynb (#27815) 
**Description:** Update outdated links for `Retrievers` and `Runnable`
in Retrievers subsection of `retrievers.ipynb`
 2024-11-01 15:42:30 +00:00
Zapiron
b0dfff4cd5 Fixed broken link for TokenTextSplitter (#27824) 
Fixed the broken redirect link for `TokenTextSplitter` section
 2024-11-01 11:32:07 -04:00
William FH
b4cb2089a2 langchain[patch]: Add warning in react agent (#26980) 2024-10-31 22:29:34 +00:00
Eugene Yurtsev
2f6254605d docs: fix more links (#27809) 
Fix more broken links
 2024-10-31 17:15:46 -04:00