Commit Graph

8083 Commits

Author SHA1 Message Date
Erick Friis
49f3cc0f6b
templates: bump lockfile deps (#19001) 2024-03-13 01:25:45 +00:00
Erick Friis
2ffb2144a6
experimental[patch]: release 0.0.54 (#19000) 2024-03-13 00:38:46 +00:00
Erick Friis
873d06c009
langchain[patch]: release 0.1.12 (#18999) 2024-03-13 00:22:21 +00:00
Leonid Ganeline
9c8523b529
community[patch]: flattening imports 3 (#18939)
@eyurtsev
2024-03-12 15:18:54 -07:00
Erick Friis
af50f21765
community[patch]: release 0.0.28 (#18993) 2024-03-12 21:55:29 +00:00
Erick Friis
4881bb669c
core[patch]: release 0.1.31 (#18989) 2024-03-12 19:45:21 +00:00
Erick Friis
a29e8d8594
elasticsearch[patch]: fix integration tests for release (#18980) 2024-03-12 10:22:07 -07:00
Erick Friis
0d1f6c417c
elasticsearch[patch]: release 0.1.1 (#18978) 2024-03-12 16:46:22 +00:00
Max Jakob
911ccf9aa6
docs: elasticsearch retriever (#18965)
Add documentation notebook for `ElasticsearchRetriever`.

## Dependencies
- [ ] Release new `langchain-elasticsearch` version 0.2.0 that includes
`ElasticsearchRetriever`
2024-03-12 09:42:36 -07:00
Dobiichi-Origami
471f2ed40a
community[patch]: re-arrange the addtional_kwargs of returned qianfan structure to avoid _merge_dict issue (#18889)
fix issue: https://github.com/langchain-ai/langchain/issues/18441
PTAL, thanks
@baskaryan, @efriis, @eyurtsev, @hwchase17.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-12 05:43:56 +00:00
Naman Jain
75122646b5
core[patch]: fixed circular dependency with json schema (#18657)
**Description:** Circular dependencies when parsing references leading
to `RecursionError: maximum recursion depth exceeded` issue. This PR
address the issue by handling previously seen refs as in any typical DFS
to avoid infinite depths.

**Issue:** https://github.com/langchain-ai/langchain/issues/12163

 **Twitter handle:** https://twitter.com/theBhulawat 


- [x] **Add tests and docs**: 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.


- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-12 05:42:45 +00:00
Tymofii
0bec1f6877
commnity[patch]: refactor code for faiss vectorstore, update faiss vectorstore documentation (#18092)
**Description:** Refactor code of FAISS vectorcstore and update the
related documentation.
Details: 
 - replace `.format()` with f-strings for strings formatting;
- refactor definition of a filtering function to make code more readable
and more flexible;
- slightly improve efficiency of
`max_marginal_relevance_search_with_score_by_vector` method by removing
unnecessary looping over the same elements;
- slightly improve efficiency of `delete` method by using set data
structure for checking if the element was already deleted;

**Issue:** fix small inconsistency in the documentation (the old example
was incorrect and unappliable to faiss vectorstore)

**Dependencies:** basic langchain-community dependencies and `faiss`
(for CPU or for GPU)

**Twitter handle:** antonenkodev
2024-03-11 22:33:03 -07:00
Roshan Santhosh
acf1ecc081
langchain[patch]: update llm_router.py (#18865)
Issue : _call method of LLMRouterChain uses predict_and_parse, which is
slated for deprecation.

Description : Instead of using predict_and_parse, this replaces it with
individual predict and parse functions.
2024-03-11 22:30:07 -07:00
Bagatur
18de77cc8c
core[minor]: add streaming support to OAI tool parsers (#18940)
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-03-11 21:53:56 -07:00
Bagatur
e0e688a277
core[minor]: generation info on msg (#18592)
related to #16403 #17188
2024-03-12 04:43:17 +00:00
Tomaz Bratanic
cda43c5a11
experimental[patch]: Fix LLM graph transformer default prompt (#18856)
Some LLMs do not allow multiple user messages in sequence.
2024-03-11 20:11:52 -07:00
Bagatur
19721246f5
core[patch]: support labeled json schema as tools (#18935) 2024-03-11 19:51:35 -07:00
Jacob Lee
950ab056eb
templates[patch]: Update pirate-speak deps, add messages placeholder (#18949)
CC @efriis
2024-03-11 19:20:30 -07:00
Leonid Ganeline
fad308a764
docs: providers update 2 (#18407)
Formatted pages into a consistent form. Added descriptions and links
when needed.
2024-03-11 18:35:37 -07:00
Erick Friis
239f0a615e
templates: redis multi-modal multi-vector rag (#18946)
---------

Co-authored-by: Tyler Hutcherson <tyler.hutcherson@redis.com>
2024-03-12 00:32:25 +00:00
Bagatur
915c1f8673
infra: rm api build CI (#18944) 2024-03-11 16:12:34 -07:00
Brace Sproul
578e67c017
docs[patch]: properly load/use env vars (#18942) 2024-03-11 15:38:05 -07:00
Erick Friis
0d888a65cb
core[patch]: move some attr/methods to BaseLanguageModel (#18936)
Cleans up some shared code between `BaseLLM` and `BaseChatModel`. One
functional difference to make it more consistent (see comment)
2024-03-11 14:59:45 -07:00
Brace Sproul
4ff6aa5c78
docs[minor]: Swap gtag for supabase (#18937)
Added deps:
- `@supabase/supabase-js` - for sending inserts
- `supabase` - dev dep, for generating types via cli
- `dotenv` for loading env vars

Added script:
- `yarn gen` - will auto generate the database schema types using the
supabase CLI. Not necessary for development, but is useful. Requires
authing with the supabase CLI (will error out w/ instructions if you're
not authed).

Added functionality:
- pulls users IP address (using a free endpoint: `https://api.ipify.org`
so we can filter out abuse down the line)

TODO:
- [x] add env vars to vercel
2024-03-11 14:23:12 -07:00
aditya thomas
5c2f7e6b2b
partners[openai]: update the docstring of OpenAI, OpenAIEmbeddings and ChatOpenAI classes (#18908)
**Description:** Update the docstring of OpenAI, OpenAIEmbeddings and
ChatOpenAI classes
**Issue:** Update import module paths to the current LangChain API
**Dependencies:** None
**Lint and test**: `make format` and `make lint` were run

This incorporates the review comments from langchain-ai/langchain#18637
which I closed due to an issue I had in updating that pr branch

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-03-11 20:48:54 +00:00
Leonid Ganeline
11195cfa42
community[patch]: speed up import times in the community package (#18928)
This PR speeds up import times in the community package
2024-03-11 16:37:36 -04:00
fjk
a7fc731720
docs: change sparkllm spark_app_url to spark_api_url (#18000)
community: fix - change sparkllm spark_app_url to spark_api_url

- **Description:** 
- Change the variable name from `sparkllm spark_app_url` to
`spark_api_url` in the community package.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-11 20:01:30 +00:00
Sevin F. Varoglu
8639624d40
docs: update OctoAI doc (#18913)
This PR updates the OctoAI LLM doc.
2024-03-11 13:01:10 -07:00
Alexander Kozlov
a7500ab0fb
docs: Update huggingface pipelines notebook (#18801) 2024-03-11 20:00:31 +00:00
Conroy Whitney
96d7fe0f85
docs: Change saved/configured chain variable name (#18863)
**Description:**
Variable name was `openai_poem` but it didn't pass in the `"prompt":
"poem"` config, so the examples were showing a joke being returned from
a variable called `*_poem`.

We could have gone one of two ways:

1. Updating the config line and the output line, or
2. Updating the variable name

The latter seemed simpler, so that's what I went with. But I'd be glad
to re-do this PR if you prefer the former.

Thanks for everything, y'all. You rock 🤘

**Issue:** N/A

**Dependencies:** N/A

**Twitter handle:** `conroywhitney`
2024-03-11 12:59:24 -07:00
aditya thomas
8544f748f2
community[patch]: update AnthropicLLM deprecation message (#18869)
**Description:** Update AnthropicLLM deprecation message import path for
ChatAnthropic
**Issue:** Incorrect import path in deprecation message
**Dependencies:** None
**Lint and test**: `make format`, `make lint` and `make test` were run
2024-03-11 12:59:10 -07:00
Virat Singh
cafffe8a21
community: Add PolygonAggregates tool (#18882)
**Description:**
In this PR, I am adding a `PolygonAggregates` tool, which can be used to
get historical stock price data (called aggregates by Polygon) for a
given ticker.

Polygon
[docs](https://polygon.io/docs/stocks/get_v2_aggs_ticker__stocksticker__range__multiplier___timespan___from___to)
for this endpoint.

**Twitter**: 
[@virattt](https://twitter.com/virattt)
2024-03-11 11:58:10 -07:00
Bagatur
2d172181e0
Revert "update api build script (#18930)" (#18931) 2024-03-11 11:47:18 -07:00
Bagatur
def329b5f2
update api build script (#18930) 2024-03-11 11:44:37 -07:00
Bagatur
c24c871d88
docs: update readme diagram (#18929) 2024-03-11 11:17:45 -07:00
Bagatur
34284c25d4
docs: turn on link check (#18924) 2024-03-11 10:50:39 -07:00
Erick Friis
93ef8ead0b
mongodb[patch]: fix core dep (#18926) 2024-03-11 10:27:29 -07:00
Mohammad Mohtashim
43db4cd20e
core[major]: On Tool End Observation Casting Fix (#18798)
This PR updates the on_tool_end handlers to return the raw output from the tool instead of casting it to a string. 

This is technically a breaking change, though it's impact is expected to be somewhat minimal. It will fix behavior in `astream_events` as well.

Fixes the following issue #18760 raised by @eyurtsev

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2024-03-11 10:59:04 -04:00
Prashanth Rao
a96a6e0f2c
docs: Fix typo and add KùzuDB to graphs docs (#18915)
- **Description:** Adding Kùzu (an embedded graph DB that uses Cypher)
to the graph docs, and fixing a typo
 - **Issue:** docs update
2024-03-11 14:42:46 +00:00
aditya thomas
3d15498612
docs: Update callbacks documentation (#18899)
**Description:** Update callbacks documentation
**Issue:** Change some module imports and a method invocation to reflect
the current LangChainAPI
**Dependencies:** None
2024-03-11 10:40:11 -04:00
Massimiliano Pronesti
8113d612bb
community[patch]: support modin document loader (#18866)
Langchain community document loaders support `pyspark`, `polars`, and
`pandas` dataframes but not `modin`'s. This PR addresses this point.
2024-03-10 18:40:04 -07:00
Leonid Ganeline
dee256ef5a
docs: platforms/google fixed broken links (#18878)
Several links are broken. Fixed them.
2024-03-10 18:19:43 -07:00
Pol Ruiz Farre
a7f63d8cb4
community[patch]: Fix BasePDFLoader suffix for s3 presigned urls (#18844)
BasePDFLoader doesn't parse the suffix of the file correctly when
parsing S3 presigned urls. This fix enables the proper detection and
parsing of S3 presigned URLs to prevent errors such as `OSError: [Errno
36] File name too long`.
No additional dependencies required.
2024-03-11 00:58:51 +00:00
Joshua Carroll
ddaf9de169
community: Fix bug with StreamlitChatMessageHistory (#18834)
- **Description:** Fix Streamlit bug which was introduced by
https://github.com/langchain-ai/langchain/pull/18250, update integration
test
- **Issue:** https://github.com/langchain-ai/langchain/issues/18684
- **Dependencies:** None
2024-03-09 13:42:22 -08:00
Kushagra
5fcbe9dd2a
community[patch]: documented the feature to filter documents in MongoDBloader (#18842)
"community[docs]: documented the feature to filter documents in
MongoDBloader"
- Description: documented the feature to filter documents in
MongoDBloader
- Feature: the feature
https://github.com/langchain-ai/langchain/discussions/18251
- Dependencies: No
- Twitter handle: https://twitter.com/im_Kushagra
2024-03-09 13:41:34 -08:00
Ikko Eltociear Ashimine
c3580d3c64
docs: fix typo in google_cloud_sql_mysql.ipynb (#18847)
arbitary -> arbitrary
2024-03-09 13:39:36 -08:00
Luan Fernandes
5a006f7264
docs: update typo in docs about agent tools (#18850)
fixes #18849
2024-03-09 13:39:18 -08:00
Leonid Ganeline
3dabd3f214
docs: platform pages update (#17836)
`Integrations` platform page ToC-s: sections there are placed without
order. For example, the
[google](https://python.langchain.com/docs/integrations/platforms/google)
page. The `LLM` section is not the first section, as it is in the
[Components](https://python.langchain.com/docs/integrations/components)
menu.
Updates:
* reorganized the page sections so they follow the Component menu order.
* fixed names for the section names: "Text Embedding Models" ->
"Embedding Models"
2024-03-09 13:34:33 -08:00
Leonid Ganeline
07c518ad3e
docs: providers update 4 (#18540)
Created the `facebook` page from `facebook_faiss` and `facebook_chat`
pages. Added another Facebook integrations into this page.
Updated `discord` page.
2024-03-09 13:30:48 -08:00
Leonid Ganeline
9c0f84ae95
docs: providers update 6 (#18610)
Cleaned up the `Integrations/Components/Memory` navbar by shortening the
page titles. Updated page titles and file names to consistent formats.
2024-03-09 13:29:44 -08:00