Commit Graph

5224 Commits

Author SHA1 Message Date
Bagatur
bd74eba152
add azure openai sched tests (#11723) 2023-10-12 10:48:45 -07:00
Nuno Campos
b54727fbad
Nc/why lcel (#11717)
<!-- Thank you for contributing to LangChain!

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,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **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` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

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/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-10-12 17:52:20 +01:00
Bagatur
9c0584be74
bump 313 (#11718) 2023-10-12 09:48:54 -07:00
Johnny Deuss
bb2ed4615c
Fix typos (#11663) 2023-10-12 11:44:03 -04:00
sudranga
361f8e1bc6
Add MMR functionality to elasticsearch retriever (#11633)
Allows MMR functionality only for the case where we have access to the
embedding function. Also allows for users to request for fields from
elasticsearch store. These are added to the document metadata.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-12 08:42:32 -07:00
Dmitry Tyumentsev
ead9d5b55c
Add yandex stt parser (#11435)
Description: Introducing an ability to load a transcription document of
audio file using [Yandex
SpeechKit](https://cloud.yandex.com/en-ru/services/speechkit)
Issue: None
Dependencies: yandex-speechkit
Tag maintainer: @rlancemartin, @eyurtsev
2023-10-12 08:42:03 -07:00
Janos Tolgyesi
15687a28d5
Use correct tokenizer for Bedrock/Anthropic LLMs (#11561)
**Description**

This PR implements the usage of the correct tokenizer in Bedrock LLMs,
if using anthropic models.

**Issue:** #11560

**Dependencies:** optional dependency on `anthropic` python library.

**Twitter handle:** jtolgyesi


---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-12 08:41:52 -07:00
kYLe
467b082c34
Modify Anyscale integration to work with Anyscale Endpoint (#11569)
**Description:** Modify Anyscale integration to work with [Anyscale
Endpoint](https://docs.endpoints.anyscale.com/)
and it supports invoke, async invoke, stream and async invoke features

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-12 08:41:25 -07:00
plpycoin
51193309ea
Update readthedocs.py (#11110)
Only parse .html files
.svg .png favicon.ico will crash processing phase

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2023-10-12 11:32:06 -04:00
Shreyas S
70a793ca9d
Update zep_memory.ipynb (#11713)
fixed minor typos;
the your > your
on > upon
2023-10-12 10:41:19 -04:00
Surav Shrestha
e61b528c0e
Fix typos in docs/docs/use_cases/question_answering/code_understandin… (#11710)
herarchy -> hierarchy
2023-10-12 10:17:23 -04:00
Surav Shrestha
f386ac3bef
Fix typos in docs/docs/use_cases/tagging.ipynb (#11712)
funtion -> function
2023-10-12 10:17:10 -04:00
Surav Shrestha
ac73154005
Fix typos in docs/docs/use_cases/question_answering/conversational_re… (#11709)
neccessary -> necessary
2023-10-12 10:16:52 -04:00
Surav Shrestha
af9ce3c224
Fix typos in docs/docs/use_cases/chatbots.ipynb (#11707)
implemet -> implement
2023-10-12 10:16:34 -04:00
Surav Shrestha
77fcaa410a
Fix typos in docs/docs/use_cases/extraction.ipynb (#11708)
This PR has a number of typos correction. I kindly request the repo
maintainers to review this PR and merge it.
2023-10-12 10:16:17 -04:00
Nuno Campos
ca9de26f2b
Add callback function to RunnablePassthrough (#11564)
<!-- Thank you for contributing to LangChain!

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,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **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` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

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/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-10-12 15:10:16 +01:00
Nuno Campos
7f4734c0dd
Add deploy command to repos generated by cli template (#11711)
<!-- Thank you for contributing to LangChain!

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,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **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` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

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/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-10-12 15:09:21 +01:00
Nuno Campos
1c0857b53e
Fix default impl of aparse_result (#11702)
Should delegate to parse_result, not to aparse, as parse_result is a
method that some output parsers override

<!-- Thank you for contributing to LangChain!

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,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **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` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

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/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
2023-10-12 14:13:59 +01:00
nuric
44da27c07b
Add SemaDB VST wrapper (#11484)
- **Description**: Adding vectorstore wrapper for
[SemaDB](https://rapidapi.com/semafind-semadb/api/semadb).
- **Issue**: None
- **Dependencies**: None
- **Twitter handle**: semafind

Checks performed:
- [x] `make format`
- [x] `make lint`
- [x] `make test`
- [x] `make spell_check`
- [x] `make docs_build`

Documentation added:

- SemaDB vectorstore wrapper tutorial
2023-10-11 19:09:38 -07:00
hsuyuming
0b743f005b
Feature/enhance huggingfacepipeline to handle different return type (#11394)
**Description:** Avoid huggingfacepipeline to truncate the response if
user setup return_full_text as False within huggingface pipeline.

**Dependencies:** : None
**Tag maintainer:**   Maybe @sam-h-bean ?

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 19:09:03 -07:00
Leonid Kuligin
2aba9ab47e
Retriever based on GCP DocAI Warehouse (#11400)
- **Description:** implements a retriever on top of DocAI Warehouse (to
interact with existing enterprise documents)
  https://cloud.google.com/document-ai-warehouse?hl=en
  - **Issue:** new functionality
 
@baskaryan

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 19:08:53 -07:00
mvhensbergen
629d9b78fa
Make example work during pydantic transition (#11498)
**Description:**

Make the example extraction code on
https://python.langchain.com/docs/use_cases/extraction work again by
importing the langchain.pydantic_v1 lib instead of the v2.

**Issue:**

Solves issue https://github.com/langchain-ai/langchain/issues/11468

Co-authored-by: Martin van Hensbergen <martin@mvhensbergen.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 18:44:47 -07:00
Erick Friis
a477ddda45
Langsmith in readme update (#11497) 2023-10-11 18:43:52 -07:00
Leonid Kuligin
9e81ab47be
Added a better error description if processor name is wrong. (#11488)
Replace this entire comment with:
  - **Description:** added a better error description for this error
  - **Issue:** #11407 
  
  @baskaryan
2023-10-11 18:43:40 -07:00
Robert Yi
e75766b759
fix: incorrect arguments in clickhouse docstring (#11693)
fix docstring for clickhouse
2023-10-11 21:41:21 -04:00
Eugene Yurtsev
17b5090c18
Add type to Agent actions (#11682)
Add `type` to agent actions.
2023-10-11 21:33:24 -04:00
April
c14a8df2ee
wrap confluence attachment processing with a try-except block (#11503)
Prevents document loading from erroring out when an attachment is not
found at the url.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 18:13:42 -07:00
Bagatur
17439daa6a
add plan execute cookbook (#11690) 2023-10-11 18:03:13 -07:00
eajechiloae
4ba2c8ba75
Fix ClearML callback (#11472)
Handle different field names in dicts/dataframes, fixing the ClearML
callback.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 17:09:02 -07:00
ElliotKetchup
7ae8b7f065
Llama doc: add 'language' to the response message (#11543)
- **Description:** add 'language' to the reponse message in the Llama
doc,
  - **Issue:** None,
  - **Dependencies:** None,
  - **Tag maintainer:** None,
  - **Twitter handle:** None

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 17:06:04 -07:00
Lawrence Wu
93bb19f69a
Fix chains/loading.py error messages (#11688)
- **Description:** make the error messages consistent in
chains/loading.py
  - **Dependencies:** None
2023-10-11 17:05:42 -07:00
Harrison Chase
18ebce2032
fix tool async (#11689) 2023-10-11 16:40:23 -07:00
sudranga
9beb03e771
11474 (#11519)
No relevant documents may be found for a given question. In some use
cases, we could directly respond with a fixed message instead of doing
an LLM call with an empty context. This PR exposes this as an option:
response_if_no_docs_found.

---------

Co-authored-by: Sudharsan Rangarajan <sudranga@nile-global.com>
2023-10-11 16:30:15 -07:00
Shinya Maeda
1f7edcd08b
doc: Fix documentation about n-gram overlap (#11549)
Fix the documentation in
https://python.langchain.com/docs/modules/model_io/prompts/example_selectors/ngram_overlap.
It's currently declaring unrelated variables, for example, `examples`
local variable is declared twice and the first one is overwritten
immediately.
  - **Issue:** N/A
  - **Dependencies:** N/A
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
  - **Twitter handle:** @dosuken123
2023-10-11 16:26:56 -07:00
Joaquin Menendez
ef99b06362
feature: add metadata information into the embedding file before uplo… (#11553)
Replace this entire comment with:
- **Description:** In this modified version of the function, if the
metadatas parameter is not None, the function includes the corresponding
metadata in the JSON object for each text. This allows the metadata to
be stored alongside the text's embedding in the vector store.
  - 
  - **Issue:** #10924
  - **Dependencies:** None
  - **Tag maintainer:** @hwchase17
@agola11
  - **Twitter handle:** @MelliJoaco

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 16:05:13 -07:00
maks-operlejn-ds
3c83779661
Qa with anonymization (#11658)
Added demo for QA system with anonymization. It will be part of
LangChain's privacy webinar.

@hwchase17 @baskaryan @nfcampos 

Twitter handle: @MaksOpp

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 15:38:08 -07:00
Marcin Wątroba
51a3a86022
#11655 Add SQLAlchemyMd5Cache implementation (#11660)
- **Description:** Add SQLAlchemyMd5Cache implementation, 
  - **Issue:** the issue # #11655,
  - **Dependencies:** no deps,
  - **Tag maintainer:** @markowanga

---------

Co-authored-by: Marcin Wątroba <marcin.watroba@pwr.edu.pl>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 15:28:09 -07:00
Suresh Kumar Ponnusamy
70f7558db2
langchain-experimental: Add allow_list support in experimental/data_anonymizer (#11597)
- **Description:** Add allow_list support in langchain experimental
data-anonymizer package
  - **Issue:** no
  - **Dependencies:** no
  - **Tag maintainer:** @hwchase17
  - **Twitter handle:**
2023-10-11 14:50:41 -07:00
wemysschen
2363c02cf3
Bos loader (#11525)
**Description:**
Add  BaiduCloud BOS document loader.

---------

Co-authored-by: chenweixu01 <chenweixu01@baidu.com>
Co-authored-by: root <root@icoding-cwx.bcc-szzj.baidu.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 14:43:48 -07:00
Kwanghoon Choi
fbb82608cd
Fixed a bug in reporting Python code validation (#11522)
- **Description:** fixed a bug in pal-chain when it reports Python
    code validation errors. When node.func does not have any ids, the
    original code tried to print node.func.id in raising ValueError.
- **Issue:** n/a,
- **Dependencies:** no dependencies,
- **Tag maintainer:** @hazzel-cn, @eyurtsev
- **Twitter handle:** @lazyswamp

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 14:34:28 -07:00
Harrison Chase
9f39c23a13
add input type for convo retrieval chain (#11679) 2023-10-11 17:13:48 -04:00
zhaozhiming
d5e762d328
fix: Change the docs of JSONAgentOutputParser (#11594)
I am merely making some minor adjustments to the function documentation.
I hope to provide a small assistance to LangChain.
- **Description:** Change the docs of JSONAgentOutputParser. It will be
`JSON` better,
  - **Issue:** no,
  - **Dependencies:** no,
  - **Tag maintainer:** @hwchase17,
  - **Twitter handle:** Not worth mentioning.
2023-10-11 14:05:53 -07:00
Shreyas S
3cd0827785
Update kay.ipynb (#11676)
Fixed title display
2023-10-11 14:02:11 -07:00
Vinay Kakade
dd0cd98861
Add support for ChatOpenAI models in Infino callback handler (#11608)
**Description:** This PR adds support for ChatOpenAI models in the
Infino callback handler. In particular, this PR implements
`on_chat_model_start` callback, so that ChatOpenAI models are supported.
With this change, Infino callback handler can be used to track latency,
errors, and prompt tokens for ChatOpenAI models too (in addition to the
support for OpenAI and other non-chat models it has today). The existing
example notebook is updated to show how to use this integration as well.
cc/ @naman-modi @savannahar68

**Issue:** https://github.com/langchain-ai/langchain/issues/11607 

**Dependencies:** None

**Tag maintainer:** @hwchase17 

**Twitter handle:** [@vkakade](https://twitter.com/vkakade)
2023-10-11 14:00:54 -07:00
Israel Ekpo
d0603c86b6
Add Support for Azure Cosmos DB MongoDB vCore Vector Store #11627 (#11632)
This PR adds support for the Azure Cosmos DB MongoDB vCore Vector Store

https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/

https://learn.microsoft.com/en-us/azure/cosmos-db/mongodb/vcore/vector-search

Summary:
- **Description:** added vector store integration for Azure Cosmos DB
MongoDB vCore Vector Store,
  - **Issue:** the issue # it fixes #11627,
  - **Dependencies:** pymongo dependency,
  - **Tag maintainer:** @hwchase17,
  - **Twitter handle:** @izzyacademy

---------

Co-authored-by: Israel Ekpo <israel.ekpo@gmail.com>
Co-authored-by: Israel Ekpo <44282278+izzyacademy@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-11 13:56:46 -07:00
Erick Friis
28ee6a7c12
Track ChatFireworks time to first_token (#11672) 2023-10-11 13:37:03 -07:00
Erick Friis
2c1e735403
Fix runnable docs link (#11675) 2023-10-11 13:11:23 -07:00
Eugene Yurtsev
539941281d
Fix output types for BaseChatModel (#11670)
* Should use non chunked messages for Invoke/Batch
* After this PR, stream output type is not represented, do we want to
use the union?

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2023-10-11 16:02:03 -04:00
Ikko Eltociear Ashimine
7d0dda7e41
Fix typo in baidu_qianfan_endpoint.ipynb (#11667)
enviroment -> environment
2023-10-11 16:01:18 -04:00
Bagatur
cf86447623
Start cookbook and move stuff from use cases (#11636) 2023-10-11 12:27:13 -07:00