Commit Graph

1432 Commits

Author SHA1 Message Date
M Bharat lal
67300567d3
GCSFileLoader retrieve blob custom metadata and append to document metadata (#11066)
- **Description:** GCSFileLoader retrieve blob's custom metadata and
append to document's metadata
- **Issue:** #9975,
- **Tag maintainer:** @baskaryan please review

Co-authored-by: b0l00ib <bharat.lal@walmart.com>
2023-10-17 12:17:59 -07:00
billytrend-cohere
f4742dce50
Add Cohere retrieval augmented generation to retrievers (#11483)
Add Cohere retrieval augmented generation to retrievers

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-17 11:51:04 -07:00
刘 方瑞
0a24ac7388
Revised notebook and add delete to MyScale vector store (#11848)
- **Description:** 
  - Add `.delete` to myscale vector store. 
  - Revised vector store notebooks
- **Tag maintainer:** @baskaryan 
- **Twitter handle:** @myscaledb @mpsk_liu
2023-10-17 11:42:21 -07:00
John Mai
3fb5e4d185
Add Baichuan chat model (#11923)
Description: A large language models developed by Baichuan Intelligent
Technology,https://www.baichuan-ai.com/home
Issue: None
Dependencies: None
Tag maintainer:
Twitter handle:
2023-10-17 11:30:57 -07:00
Eugene Yurtsev
9ecb7240a4
Add security note to recursive url loader (#11934)
Add security note to recursive loader
2023-10-17 13:41:43 -04:00
maks-operlejn-ds
42dcc502c7
Anonymizer small fixes (#11915) 2023-10-17 10:27:29 -07:00
Eugene Yurtsev
90e9ec6962
Sitemap specify default filter url (#11925)
Specify default filter URL in sitemap loader and add a security note

---------

Co-authored-by: Predrag Gruevski <2348618+obi1kenobi@users.noreply.github.com>
2023-10-17 13:19:27 -04:00
Bagatur
ba0d729961
bump 316 (#11928) 2023-10-17 09:47:57 -07:00
Eugene Yurtsev
12d7eaa0c2
Add security notices to toolkits (#11900)
This adds security notices to toolkits init, and to several toolkits.
We'll need to continue documenting the rest of the toolkits.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-17 11:45:09 -04:00
Eugene Yurtsev
5f4a697ce3
Add deprecation warnings (#11899)
Add deprecation warnings

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-17 10:59:38 -04:00
Nuno Campos
8b79cf9566
Add lock for using global config enum weak map (#11920)
<!-- 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.
 -->
2023-10-17 15:50:35 +01:00
Nuno Campos
2a8ded6c8c
Export merge_configs function (#11916)
<!-- 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.
 -->
2023-10-17 15:36:11 +01:00
Nuno Campos
778e7c526e Add comment 2023-10-17 15:29:39 +01:00
Nuno Campos
19319e1746 Allow configs with None values 2023-10-17 15:23:58 +01:00
Nuno Campos
b0d5882fe1 Export merge_configs function 2023-10-17 13:22:07 +01:00
Nuno Campos
12596b9a9b Add validation for configurable keys passed to .with_config()
- Fix some typing issues found while doing that
2023-10-17 08:50:31 +01:00
Nuno Campos
754aca794f remove print 2023-10-17 08:46:07 +01:00
Nuno Campos
cf448a6314 Ensure that configurable fields with enums support deduplication 2023-10-17 08:25:21 +01:00
Leonid Ganeline
31f264169d
evaluation criteria (#11681)
the updated value was:
` Criteria.MISOGYNY: "Is the submission misogynistic? If so, respond Y."
`
The " If so, respond Y." should not be here. This sub-string is not
presented in any other criteria and should not be presented here.
I also added a synonym to "misogynistic" as it done in many other
criteria.
2023-10-16 21:05:08 -07:00
Dmitry Tyumentsev
e8c1850369
Add YandexGPT LLM and Chat model (#11703)
**Description:** Introducing an ability to work with the
[YandexGPT](https://cloud.yandex.com/en/services/yandexgpt) language
model.
2023-10-16 20:30:07 -07:00
Bagatur
c15701eebf
Revert "Add baichuan model" (#11901)
cc @cloudscool, apologies your PR wasn't actually passing CI
2023-10-16 20:01:12 -07:00
cloudscool
c1d811c4bc
Add baichuan model 2023-10-16 19:27:35 -07:00
John Mai
0169d45ba8
Supported OutputFixingParser max_retries (#11754)
Description: Supported OutputFixingParser max_retries
 - max_retries: Maximum number of retries to parser.

Issue: None
Dependencies: None
Tag maintainer: @baskaryan
Twitter handle: @JohnMai95

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-16 19:25:47 -07:00
volodymyr-memsql
ff8e6981ff
SingleStoreDBChatMessageHistory: Add singlestoredb support for ChatMessageHistory (#11705)
**Description**

- Added the `SingleStoreDBChatMessageHistory` class that inherits
`BaseChatMessageHistory` and allows to use of a SingleStoreDB database
as a storage for chat message history.
- Added integration test to check that everything works (requires
`singlestoredb` to be installed)
- Added notebook with usage example
- Removed custom retriever for SingleStoreDB vector store (as it is
useless)

---------

Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com>
2023-10-16 21:59:45 -04:00
Mohammad Mohtashim
634ccb8ccd
test_stream_log_retriever Unit Test + Tool names fix (#11808)
## Description



| Tool         | Original Tool Name       |
|-----------------------------|---------------------------|
| open-meteo-api              | Open Meteo API            |
| news-api                    | News API                  |
| tmdb-api                    | TMDB API                  |
| podcast-api                 | Podcast API               |
| golden_query                | Golden Query              |
| dall-e-image-generator      | Dall-E Image Generator    |
| twilio                      | Text Message              |
| searx_search_results        | Searx Search Results      |
| dataforseo                  | DataForSeo Results JSON   |

When using these tools through `load_tools`, I encountered the following
validation error:

```console
openai.error.InvalidRequestError: 'TMDB API' does not match '^[a-zA-Z0-9_-]{1,64}$' - 'functions.0.name'
```

In order to avoid this error, I replaced spaces with hyphens in the tool
names:

| Tool           | Corrected Tool Name       |
|-----------------------------|---------------------------|
| open-meteo-api              | Open-Meteo-API            |
| news-api                    | News-API                  |
| tmdb-api                    | TMDB-API                  |
| podcast-api                 | Podcast-API               |
| golden_query                | Golden-Query              |
| dall-e-image-generator      | Dall-E-Image-Generator    |
| twilio                      | Text-Message              |
| searx_search_results        | Searx-Search-Results      |
| dataforseo                  | DataForSeo-Results-JSON   |

This correction resolved the validation error.

Additionally, a unit test,
`tests/unit_tests/schema/runnable/test_runnable.py::test_stream_log_retriever`,
was failing at random. Upon further investigation, I confirmed that the
failure was not related to the above-mentioned changes. The `stream_log`
variable was generating the order of logs in two ways at random The
reason for this behavior is unclear, but in the assertion, I included
both possible orders to account for this variability.
2023-10-16 18:46:19 -07:00
Predrag Gruevski
7c0f1bf23f
Upgrade experimental package dependencies and use Poetry 1.6.1. (#11339)
Part of upgrading our CI to use Poetry 1.6.1.
2023-10-16 21:13:31 -04:00
Eugene Yurtsev
c2c0814a94
Add security notice to file management tool (#11878)
Add security notice to file management tool

---------

Co-authored-by: Predrag Gruevski <2348618+obi1kenobi@users.noreply.github.com>
2023-10-16 21:12:13 -04:00
zhaoshengbo
cb7e12f6ba
Adapt to the latest version of Alibaba Cloud OpenSearch vector store API (#11849)
Hello Folks,

Alibaba Cloud OpenSearch has released a new version of the vector
storage engine, which has significantly improved performance compared to
the previous version. At the same time, the sdk has also undergone
changes, requiring adjustments alibaba opensearch vector store code to
adapt.

This PR includes:

Adapt to the latest version of Alibaba Cloud OpenSearch API.
More comprehensive unit testing.
Improve documentation.

I have read your contributing guidelines. And I have passed the tests
below

- [x] make format
- [x]  make lint
- [x]  make coverage
- [x]  make test

---------

Co-authored-by: zhaoshengbo <shengbo.zsb@alibaba-inc.com>
2023-10-16 18:07:24 -07:00
Lee
e669f9d731
Fix: Sitemap Document Loader Tests and Documentation (#11866)
**Description:**
While working on the Docusaurus site loader #9138, I noticed some
outdated docs and tests for the Sitemap Loader.

**Issue:** 
This is tangentially related to #6691 in reference to doc links. I plan
on digging in to a few of these issue when I find time next.
2023-10-16 17:42:10 -07:00
Jean-Louis Queguiner
8b697ff0ee
feat(llm): add together.xyz as an LLM provider (#11892)
- **Description:** added together.xyz as an LLM provider, 
  - **Issues:** fix some linting issues
  - twitter handle @jilijeanlouis 

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-16 17:08:04 -07:00
Leonid Kuligin
d269dd2e2f
added a multiturn search based on Vertex AI Search (#11885)
Replace this entire comment with:
- **Description:** Added a retriever based on multi-turn Vertex AI
Search
  - **Twitter handle:** lkuligin
2023-10-16 17:05:12 -07:00
Leonid Kuligin
38ed55245f
added Vertex examples as attributes (#11890)
- **Description:** added examples to Vertex chat models as optional
class attributes, so that a model with examples can be used inside a
chain
  - **Twitter handle:** lkuligin
2023-10-16 16:55:45 -07:00
eryk-dsai
5019f59724
fix: more robust check whether the HF model is quantized (#11891)
Removes the check of `model.is_quantized` and adds more robust way of
checking for 4bit and 8bit quantization in the `huggingface_pipeline.py`
script. I had to make the original change on the outdated version of
`transformers`, because the models had this property before. Seems
redundant now.

Fixes: https://github.com/langchain-ai/langchain/issues/11809 and
https://github.com/langchain-ai/langchain/issues/11759
2023-10-16 16:54:20 -07:00
Eugene Yurtsev
210a48cfb5
Add security considerations (#11869)
Add security considerations to existing graph tools.
2023-10-16 12:23:48 -04:00
Bagatur
25b1d65305
bump 315 (#11850) 2023-10-16 00:50:54 -07:00
Nuno Campos
4321d192ea
Use a less specific return type for | on Runnables (#11762)
<!-- 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.
 -->

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-15 21:15:06 +01:00
Harrison Chase
a506302772
bearly tool (#11812) 2023-10-14 16:03:58 -07:00
Harrison Chase
4a2f0c51a1
use get_llm_cache and set_llm_cache (#11741)
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-14 09:29:30 -07:00
Harrison Chase
f3ad22e64a
pipe default key (#11788) 2023-10-14 08:39:23 +01:00
Eugene Yurtsev
0d37b4c27d
Add python,pandas,xorbits,spark agents to experimental (#11774)
See for contex
https://github.com/langchain-ai/langchain/discussions/11680
2023-10-13 17:36:44 -04:00
Michael Feil
233a904f2e
GradientLLM Docs update and model_id renaming. (#10963)
Related to #10800 

- Errors in the Docstring of GradientLLM / Gradient.ai LLM
- Renamed the `model_id` to `model` and adapting this in all tests.
Reason to so is to be in Sync with `GradientEmbeddings` and other LLM's.
- inmproving tests so they check the headers in the sent request.
- making the aiosession a private attribute in the docs, as in the
future `pip install gradientai` will be replacing aiosession.
- adding a example how to fine-tune on the Prompt Template as suggested
in #10800
2023-10-13 13:57:58 -07:00
Bagatur
1559ba4bfc
fix upstash test import (#11781) 2023-10-13 13:31:36 -07:00
Leonid Kuligin
9f0a718198
added candidate_count for Vertex models (#11729)
- **Description:** added support for `candidate_count` parameter on
Vertex
2023-10-13 13:31:20 -07:00
David
9d200e6cbe
Create ChatEverlyAI (#11357)
- Description: Adds the ChatEverlyAI class with llama-2 7b on [EverlyAI
Hosted
Endpoints](https://everlyai.xyz/)
- It inherits from ChatOpenAI and requires openai (probably unnecessary
but it made for a quick and easy implementation)

---------

Co-authored-by: everly-studio <127131037+everly-studio@users.noreply.github.com>
2023-10-13 12:25:11 -07:00
Hristo G
7fb25b4154
Add graceful fallback for ES vectorstore when content field is missing (#11726)
- **Description:**
- If the Elasticsearch field used for Langchain > Document.page_content
is missing because the specific document is
        somehow malformed fail gracefully.

  - **Tag maintainer:** 
    - @joemcelroy
2023-10-13 12:03:32 -07:00
Bagatur
f06fcde0d7
rm duplicate zilliz import (#11777) 2023-10-13 12:01:22 -07:00
Bagatur
a3330c4258
bump 314 (#11773) 2023-10-13 11:09:54 -07:00
Erick Friis
1861cc7100
General anthropic functions, steps towards experimental integration tests (#11727)
To match change in js here
https://github.com/langchain-ai/langchainjs/pull/2892

Some integration tests need a bit more work in experimental:
![Screenshot 2023-10-12 at 12 02 49
PM](https://github.com/langchain-ai/langchain/assets/9557659/262d7d22-c405-40e9-afef-669e8d585307)

Pretty sure the sqldatabase ones are an actual regression or change in
interface because it's returning a placeholder.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-10-13 09:48:24 -07:00
Nuno Campos
17c69678ab
Revert "New add Baichuan Model" (#11761)
Reverts langchain-ai/langchain#11714

This has linting and formatting issues, plus it's added to chat models
folder but doesn't subclass Chat Model base class
2023-10-13 08:23:15 -07:00
cloudscool
56653c53aa
New add Baichuan Model (#11714)
Motivation and Context
At present, the Baichuan Large Language Model is relatively popular and
efficient in performance. Due to widespread market recognition, this
model has been added to enhance the scalability of Langchain's ability
to access the big language model, so as to facilitate application access
and usage for interested users.

System Info
langchain: 0.0.295
python:3.8.3
IDE:vs code

Description
Add the following files:

1. Add baichuan_baichuaninc_endpoint.py in the
libs/langchain/langchain/chat_models
2. Modify the __init__.py file,which is located in the
libs/langchain/langchain/chat_models/__init__.py:
a. Add "from langchain.chat_models.baichuan_baichuaninc_endpoint import
BaichuanChatEndpoint"
    b. Add "BaichuanChatEndpoint" In the file's __ All__  method

Your contribution
I am willing to help implement this feature and submit a PR, but I would
appreciate guidance from the maintainers or community to ensure the
changes are made correctly and in line with the project's standards and
practices.
2023-10-12 23:04:28 -07:00