Commit Graph

7350 Commits

Author SHA1 Message Date
Mohammad Mohtashim
1fa056c324
community[patch]: Don't set search path for unknown SQL dialects (#16047)
- **Description:** Made a small fix for the `SQLDatabase` highlighted in
an issue. The issue pertains to switching schema for different SQL
engines. 
  - **Issue:** #16023
@baskaryan
2024-01-17 10:31:11 -08:00
Erick Friis
11327e6b64
google-vertexai[patch]: typing, release 0.0.2 (#16153) 2024-01-17 10:16:59 -08:00
Leonid Ganeline
2709d3e5f2
langchain[patch]: updated imports for langchain.callbacks (#16060)
Updated imports from 'langchain` to `core` where it is possible

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-01-17 10:06:59 -08:00
Leonid Ganeline
c5f6b828ad
langchain[patch], community[minor]: move output_parsers.ernie_functions (#16057)
`output_parsers.ernie_functions` moved into `community`
2024-01-17 10:06:18 -08:00
Bagatur
e7ddec1f2c
docs: change parallel doc name (#16152) 2024-01-17 10:04:34 -08:00
Leonid Ganeline
49aff3ea5b
langchain[patch]: updated agents imports (#16061)
Updated imports into `langchain` to `core` where it is possible

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-01-17 10:02:29 -08:00
Leonid Ganeline
60b1bd02d7
langchain[patch]: updated imports for output_parsers (#16059)
Updated imports from `langchain` to `core` where it is possible
2024-01-17 10:02:12 -08:00
Leonid Ganeline
9e9ad9b0e9
langchain[patch]: updated retrievers imports (#16062)
Updated imports into `langchain` to `core` where it is possible

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-01-17 10:01:06 -08:00
Leonid Ganeline
d350be959d
langchain[patch]: updated chains imports (#16064)
Updated imports into `langchain` to `core` where it is possible

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-01-17 09:58:42 -08:00
Fei Wang
d0e101e4e0
community[patch]: fix ollama astream (#16070)
Update ollama.py
2024-01-17 09:42:41 -08:00
Joshua Carroll
bc0cb1148a
docs: Fix StreamlitChatMessageHistory docs to latest API (#16072)
- **Description:** Update [this
page](https://python.langchain.com/docs/integrations/memory/streamlit_chat_message_history)
to use the latest API
  - **Issue:** https://github.com/langchain-ai/langchain/issues/13995
  - **Dependencies:** None
  - **Twitter handle:** @OhSynap
2024-01-17 09:42:10 -08:00
ChengZi
8597484195
langchain[patch]: support more comparators in Milvus self-querying retriever (#16076)
- **Description:** Support IN and LIKE comparators in Milvus
self-querying retriever, based on [Boolean Expression
Rules](https://milvus.io/docs/boolean.md)
  - **Issue:** No
  - **Dependencies:** No
  - **Twitter handle:** No

Signed-off-by: ChengZi <chen.zhang@zilliz.com>
2024-01-17 09:41:23 -08:00
David DeCaprio
9c2f1f07a0
docs: Updated SQLite example to use LCEL and SQLChatMessageHistory (#16094)
- **Description:** Updated the SQLite example integration notebook to
latest standards
- **Issue:**
[15664](https://github.com/langchain-ai/langchain/issues/15664)
  - **Dependencies:** None
  - **Twitter handle:** @davedecaprio
2024-01-17 09:39:44 -08:00
Kapil Sachdeva
f406dc3872
docs: in RunnableRetry, correct the example snippet that uses with_retry method on Runnable (#16108)
The example code snippet for with_retry is using incorrect argument
names. This PR fixes that
2024-01-17 09:11:27 -08:00
Abhinav
da96c511d1
docs: Replace azure_cosmos_db_vector_search with azure_cosmos_db in Cosmos DB Documentation (#16122)
**Description**: This PR fixes an error in the documentation for Azure
Cosmos DB Integration.
**Issue**: The correct way to import `AzureCosmosDBVectorSearch` is
```python
from langchain_community.vectorstores.azure_cosmos_db import (
    AzureCosmosDBVectorSearch,
)
```
While the
[documentation](https://python.langchain.com/docs/integrations/vectorstores/azure_cosmos_db)
states it to be
```python
from langchain_community.vectorstores.azure_cosmos_db_vector_search import (
    AzureCosmosDBVectorSearch,
    CosmosDBSimilarityType,
)
```
As you can see in
[azure_cosmos_db.py](c323742f4f/libs/langchain/langchain/vectorstores/azure_cosmos_db.py (L1C45-L2))
**Dependencies:**: None
**Twitter handle**: None
2024-01-17 09:11:16 -08:00
BeatrixCohere
b0c3e3db2b
community[patch]: Handle when documents are not provided in the Cohere response (#16144)
- **Description:** This handles the cohere response when documents
aren't included in the response
  - **Issue:** N/A
  - **Dependencies:** N/A
  - **Twitter handle:** N/A
2024-01-17 09:11:00 -08:00
Felix Krones
d91126fc64
community[patch]: missing unpack operator for or_clause in pgvector document filter (#16148)
- Fix for #16146 
- Adding unpack operation to "or" and "and" filter for pgvector
retriever. #
2024-01-17 09:10:43 -08:00
purificant
3606c5d5e9
infra: update poetry 1.6.1 -> 1.7.1 (#15027) 2024-01-17 08:51:20 -08:00
Ikko Eltociear Ashimine
a35e5f19a8
docs: Update gradient.ipynb (#16149)
Enviroment -> Environment
2024-01-17 08:48:24 -08:00
Erick Friis
06fe2f4fb0
partners: add license field (#16117)
- bumps package post versions for packages without current unreleased
updates
- will bump package version in release prs associated with packages that
do have changes (mistral, vertex)
2024-01-17 08:37:13 -08:00
Erick Friis
ce10fe0c2f
mistralai[patch]: release 0.0.3 (#16116)
embeddings
2024-01-17 08:36:05 -08:00
William FH
e5cf1e2414
Community[patch]use secret str in Tavily and HuggingFaceInferenceEmbeddings (#16109)
So the api keys don't show up in repr's 

Still need to do tests
2024-01-17 00:30:07 -08:00
William FH
f3601b0aaf
Community[Patch] Remove docs form bm25 repr (#16110)
Resolves: https://github.com/langchain-ai/langsmith-sdk/issues/356
2024-01-17 00:00:55 -08:00
David
c323742f4f
mistralai[minor]: Add embeddings (#15282)
- **Description:** Adds MistralAIEmbeddings class for embeddings, using
the new official API.
- **Dependencies:** mistralai
- **Tag maintainer**: @efriis, @hwchase17
- **Twitter handle:** @LMS_David_RS

Create `integrations/text_embedding/mistralai.ipynb`: an example
notebook for MistralAIEmbeddings class
Modify `embeddings/__init__.py`: Import the class
Create `embeddings/mistralai.py`: The embedding class
Create `integration_tests/embeddings/test_mistralai.py`: The test file.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-01-16 17:48:37 -08:00
Leonid Ganeline
f974eb5b8b
docs: updated Anyscale page (#16107)
- added description
- fixed broken links
- added setting instructions
- added the Chat model reference
2024-01-16 17:13:51 -08:00
Leonid Kuligin
4df14a61fc
google-vertexai[minor]: add function calling on VertexAI (#15822)
Replace this entire comment with:
  - **Description:** Description: added support for tools on VertexAI
  - **Issue:** #15073 
  - **Twitter handle:**  lkuligin

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-01-16 17:01:26 -08:00
Bagatur
8840a8cc95
docs: tool-use use case (#15783)
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2024-01-16 10:41:14 -08:00
Bagatur
3d34347a85
langchain[patch]: bump core dep to 0.1.9 (#16104) 2024-01-16 10:39:07 -08:00
Bagatur
62a2e9ee19
langchain[patch]: Release 0.1.1 (#16103) 2024-01-16 10:17:38 -08:00
Christophe Bornet
6b6269441c
docs: Add page for AstraDB self retriever (#16077)
Preview:
https://langchain-git-fork-cbornet-astra-self-retriever-docs-langchain.vercel.app/docs/integrations/retrievers/self_query/astradb
2024-01-16 09:50:30 -08:00
Juan Bustos
5f057f24ac
docs: Update elasticsearch.ipynb (#16090)
Fixed a typo, the parameter used for the Elasticsearch API key was
called api_key, but the parameter is called es_api_key.
2024-01-16 09:49:42 -08:00
Bagatur
076593382a
core[patch]: Release 0.1.11 (#16100) 2024-01-16 09:46:04 -08:00
Bagatur
c5656a4905
core[patch]: pass exceptions to fallbacks (#16048) 2024-01-16 09:36:43 -08:00
Nuno Campos
770f57196e
Add unit test for overridden lc_namespace (#16093) 2024-01-16 09:22:52 -08:00
Erick Friis
52114bdfac
community[patch]: release 0.0.13 (#16087) 2024-01-16 06:25:28 -08:00
James Briggs
ca288d8f2c
community[patch]: add vector param to index query for pinecone vec store (#16054) 2024-01-16 06:12:19 -08:00
Antonio Morales
476fb328ee
community[patch]: implement adelete from VectorStore in Qdrant (#16005)
**Description:**
Implement `adelete` function from `VectorStore` in `Qdrant` to support
other asynchronous flows such as async indexing (`aindex`) which
requires `adelete` to be implemented. Since `Qdrant` can be passed an
async qdrant client, this can be supported easily.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-01-15 19:57:09 -08:00
Bagatur
697a6f2c80
langchain[patch]: fix requests lint (#16049) 2024-01-15 12:54:30 -08:00
高远
061e63eef2
community[minor]: add vikingdb vecstore (#15155)
---------

Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>
2024-01-15 12:34:01 -08:00
andrijdavid
d196646811
community[patch]: Refactor OpenAIWhisperParserLocal (#15150)
This PR addresses an issue in OpenAIWhisperParserLocal where requesting
CUDA without availability leads to an AttributeError #15143

Changes:

- Refactored Logic for CUDA Availability: The initialization now
includes a check for CUDA availability. If CUDA is not available, the
code falls back to using the CPU. This ensures seamless operation
without manual intervention.
- Parameterizing Batch Size and Chunk Size: The batch_size and
chunk_size are now configurable parameters, offering greater flexibility
and optimization options based on the specific requirements of the use
case.

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2024-01-15 12:29:14 -08:00
Zhichao HAN
5cf06db3b3
community[minor]: add JsonRequestsWrapper tool (#15374)
**Description:** This new feature enhances the flexibility of pipeline
integration, particularly when working with RESTful APIs.
``JsonRequestsWrapper`` allows for the decoding of JSON output, instead
of the only option for text output.

---------

Co-authored-by: Zhichao HAN <hanzhichao2000@hotmail.com>
2024-01-15 12:27:19 -08:00
chyroc
d334efc848
community[patch]: fix top_p type hint (#15452)
fix: https://github.com/langchain-ai/langchain/issues/15341

@efriis
2024-01-15 11:59:39 -08:00
Mateusz Szewczyk
251afda549
community[patch]: fix stop (stop_sequences) param on WatsonxLLM (#15541)
- **Description:** Fix to IBM
[watsonx.ai](https://www.ibm.com/products/watsonx-ai) LLM provider (stop
(`stop_sequences`) param on watsonxLLM)
- **Dependencies:**
[ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/),
2024-01-15 11:44:57 -08:00
Funkeke
7220124368
community[patch]: fix tongyi completion and params error (#15544)
fix tongyi completion json parse error and prompt's params error

---------

Co-authored-by: fangkeke <3339698829@qq.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2024-01-15 11:43:13 -08:00
Averi Kitsch
ee378a0f40
docs: add page for Firestore Chat Message History integration (#15554)
- **Description:** Adds documentation for the
`FirestoreChatMessageHistory` integration and lists integration in
Google's documentation
  - **Issue:** NA
  - **Dependencies:** No

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2024-01-15 11:42:33 -08:00
盐粒 Yanli
ddf4e7c633
community[minor]: Update pgvecto_rs to use its high level sdk (#15574)
- **Description:** Update pgvecto_rs to use its high level sdk, 
  - **Issue:** fix #15173
2024-01-15 11:41:59 -08:00
YHW
ce21392a21
community: add a flag that determines whether to load the milvus collection (#15693)
fix https://github.com/langchain-ai/langchain/issues/15694

---------

Co-authored-by: hyungwookyang <hyungwookyang@worksmobile.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-01-15 11:25:23 -08:00
Mohammad Mohtashim
9e779ca846
community[patch]: Fixing the SlackGetChannel Tool Input Error (#15725)
Fixed the issue mentioned in #15698 for SlackGetChannel Tool.

@baskaryan.

---------

Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-01-15 11:23:55 -08:00
axiangcoding
daa9ccae52
community[patch]: deprecate ErnieBotChat and ErnieEmbeddings classes (#15862)
- **Description:** add deprecated warning for ErnieBotChat and
ErnieEmbeddings.
- These two classes **lack maintenance** and do not use the sdk provided
by qianfan, which means hard to implement some key feature like
streaming.
- The alternative `langchain_community.chat_models.QianfanChatEndpoint`
and `langchain_community.embeddings.QianfanEmbeddingsEndpoint` can
completely replace these two classes, only need to change configuration
items.
  - **Issue:** None,
  - **Dependencies:** None,
  - **Twitter handle:** None

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-01-15 11:14:44 -08:00
Eugene Yurtsev
7c57cfd8f0
docs: Update OpenAI functions agent (#15894)
Add info and a tip explaining when to use this agent.
2024-01-15 11:14:29 -08:00