Commit Graph

9297 Commits

Author SHA1 Message Date
ccurme
3390dc2266
docs: style nits (#21666) 2024-05-14 10:18:13 -04:00
ccurme
2463c8060c
docs: how-to on adding scores to retriever results (#21626) 2024-05-14 09:41:36 -04:00
Zhao Blake
972d2071c6
core[patch]: Fix typo in VectorStoreExampleSelector doc-string (#21574) 2024-05-14 13:31:37 +00:00
William FH
714cba96a8
[docs] Update langgraph migration guide (#21644)
- add links to references where appropriate
- use the create_react_agent
- Fix the timeout recommendation
2024-05-14 06:13:17 +00:00
Erick Friis
5144c94603
docs: add 0.2 search notice (#21653) 2024-05-14 04:00:18 +00:00
Erick Friis
2a984e8e3f
docs: huggingface package (#21645) 2024-05-14 03:17:40 +00:00
Anush
cd1879f5e7
docs: Qdrant partner package reference (#21649)
## Description:
As the title goes.
2024-05-13 19:51:57 -07:00
Erick Friis
c77d2f2b06
multiple: core 0.2 nonbreaking dep, check_diff community->langchain dep (#21646)
0.2 is not a breaking release for core (but it is for langchain and
community)

To keep the core+langchain+community packages in sync at 0.2, we will
relax deps throughout the ecosystem to tolerate `langchain-core` 0.2
2024-05-13 19:50:36 -07:00
Anush
edd68e4ad4
qdrant: init package (#21146)
## Description

This PR introduces the new `langchain-qdrant` partner package, intending
to deprecate the community package.

## Changes

- Moved the Qdrant vector store implementation `/libs/partners/qdrant`
with integration tests.
- The conditional imports of the client library are now regular with
minor implementation improvements.
- Added a deprecation warning to
`langchain_community.vectorstores.qdrant.Qdrant`.
- Replaced references/imports from `langchain_community` with either
`langchain_core` or by moving the definitions to the `langchain_qdrant`
package itself.
- Updated the Qdrant vector store documentation to reflect the changes.

## Testing
- `QDRANT_URL` and
[`QDRANT_API_KEY`](583e36bf6b)
env values need to be set to [run integration
tests](d608c93d1f)
in the [cloud](https://cloud.qdrant.tech).
- If a Qdrant instance is running at `http://localhost:6333`, the
integration tests will use it too.
- By default, tests use an
[`in-memory`](https://github.com/qdrant/qdrant-client?tab=readme-ov-file#local-mode)
instance(Not comprehensive).

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Erick Friis <erickfriis@gmail.com>
2024-05-13 18:20:03 -07:00
Erick Friis
fe8c9d621a
docs: ignore nb echo:false blocks (#21624)
not working currently
2024-05-13 17:18:26 -07:00
Prashanth Rao
63c3a0e56c
[community][graph]: Update KuzuQAChain and docs (#21218)
This PR makes some small updates for `KuzuQAChain` for graph QA.

- Updated Cypher generation prompt (we now support `WHERE EXISTS`) and
generalize it more
- Support different LLMs for Cypher generation and QA
- Update docs and examples
2024-05-13 17:17:14 -07:00
Bagatur
752b1e85f8
docs: gh feedback link (#21606)
Co-authored-by: bracesproul <braceasproul@gmail.com>
2024-05-14 00:11:37 +00:00
Bagatur
506df439eb
docs: how to index nits (#21623) 2024-05-13 23:52:50 +00:00
Bagatur
b514a479c0
docs: standardize capitalization (#21641) 2024-05-13 16:25:51 -07:00
Bagatur
89aae3e043
docs: add Techniques to Concepts (#21636)
- Adds Techniques section
- Moves function calling, retrieval types to Techniques
- Removes Installation section (not conceptual)
- Reorders a few things (chat models before llms, package descriptions
before diagram)
- Add text splitter types to Techniques
2024-05-13 16:06:16 -07:00
Tomaz Bratanic
89ff6a3d3b
Add sentiment and confidence levels to diffbotgraphtransformer (#21590)
Co-authored-by: Erick Friis <erickfriis@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-05-13 23:00:52 +00:00
Bagatur
526ba235f3
docs: fix prereq links (#21630) 2024-05-13 15:40:53 -07:00
Erick Friis
0541e06e21
infra: 0.2 docs 404 page (#21634) 2024-05-13 22:11:28 +00:00
Erick Friis
e861b5bcb7
infra: fix api ref link generation (#21631) 2024-05-13 14:52:26 -07:00
Erick Friis
9b51ca08bc
huggingface: fix community dep checking (#21628) 2024-05-13 21:52:18 +00:00
Erick Friis
91a2ea5cd6
chroma, mongodb: fix docstrings (#21629) 2024-05-13 21:27:43 +00:00
Jofthomas
afd85b60fc
huggingface: init package (#21097)
First Pr for the langchain_huggingface partner Package

- Moved some of the hugging face related class from `community` to the
new `partner package`

Still needed :
- Documentation
- Tests
- Support for the new apply_chat_template in `ChatHuggingFace`
- Confirm choice of class to support for embeddings witht he
sentence-transformer team.

cc : @efriis

---------

Co-authored-by: Cyril Kondratenko <kkn1993@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-05-13 20:53:15 +00:00
Tomaz Bratanic
9fce03e7db
community[patch]: Fix neo4j enhanced schema (#21582) 2024-05-13 15:26:06 -04:00
Christophe Bornet
66a4da8ad0
community[patch]: Improve Cassandra VectorStore docsctrings (#21620) 2024-05-13 15:24:26 -04:00
adreo00
40aff1eacc
core[major]: AsyncCallbackManagerForToolRun no longer casts return object to string (#20374)
- **Description:** Stops `AsyncCallbackManagerForToolRun` from
converting the output to str
- **Issue:** #20372
- **Dependencies:** None
2024-05-13 15:09:12 -04:00
Eugene Yurtsev
25fbe356b4
community[patch]: upgrade to recent version of mypy (#21616)
This PR upgrades community to a recent version of mypy. It inserts type:
ignore on all existing failures.
2024-05-13 14:55:07 -04:00
Eugene Yurtsev
b923951062
langchain[patch]: CI add lint rule for community imports (#21618)
Add a rule to check for imports from community in global scope
2024-05-13 14:51:25 -04:00
Jorge Piedrahita Ortiz
4378fbbef0
community[patch]: Fix typos in Sambanova integration doc-strings (#21617)
- **Description:** Sambanova integration docstrings updated, bad
formated

---------

Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
2024-05-13 18:35:16 +00:00
Erick Friis
0f5bf94f9f
infra: remove ai21 docs scan features (#21614)
ai21 depends on ai21-tokenizer which depends on too restrictive/old
version of `tokenizers`
2024-05-13 18:05:53 +00:00
ccurme
fe08421207
docs: add hybrid retrieval how-to guide (#21613)
Updating v0.2 docs with
https://github.com/langchain-ai/langchain/pull/21245
2024-05-13 14:03:55 -04:00
Christophe Bornet
bcf53f93e1
[community]: Add missing docstring param to CassandraLoader (#21611) 2024-05-13 16:03:18 +00:00
Christophe Bornet
e6fa4547b1
community[minor]: Add alazy_load to AsyncHtmlLoader (#21536)
Also fixes a bug that `_scrape` was called and was doing a second HTTP
request synchronously.

**Twitter handle:** cbornet_
2024-05-13 12:01:03 -04:00
Leonid Ganeline
4c48732f94
docs: providers updates 1 (#20256)
- Proviers pages: added missed integrations; fixed format
- `mistralai` converted from notebook to .mdx format
2024-05-13 11:54:51 -04:00
ccurme
15cb1133e7
docs: fix path for state_of_the_union sample file (#21609) 2024-05-13 11:46:02 -04:00
Bagatur
83a8fdcfd1
infra: fix local doc make command (#21608) 2024-05-13 08:30:30 -07:00
Eugene Yurtsev
4dc625057e
README: Update downloads to show downloads of langchain-core (#21387)
Update downloads to keep track of langchain-core
2024-05-13 11:26:50 -04:00
Wang Guan
b53548dcda
langchain[minor]: allow CacheBackedEmbeddings to cache queries (#20073)
Add optional caching of queries to cache backed embeddings
2024-05-13 15:18:04 +00:00
Guangdong Liu
a156aace2b
core[patch]:Fix Incorrect listeners parameters for Runnable.with_listeners() and .map() (#20661)
- **Issue:** fix #20509
-  @baskaryan, @eyurtsev


![image](https://github.com/langchain-ai/langchain/assets/48236177/f799a976-b983-4d8b-b373-64392e1fd6c6)
2024-05-13 11:16:17 -04:00
ccurme
b0f5a47f25
docs: update some retrievers how-to guides (#21607) 2024-05-13 11:03:33 -04:00
junkeon
480c02bf55
upstage[minor]: add merge_and_split function for document loader (#21603)
- Introduce the `merge_and_split` function in the
`UpstageLayoutAnalysisLoader`.
- The `merge_and_split` function takes a list of documents and a
splitter as inputs.
- This function merges all documents and then divides them using the
`split_documents` method, which is a proprietary function of the
splitter.
- If the provided splitter is `None` (which is the default setting), the
function will simply merge the documents without splitting them.
2024-05-13 10:55:19 -04:00
Leonid Ganeline
500569da48
community[patch]: vectorstores import update (#21169)
Issue: we have several helper functions to import third-party libraries
like lancedb.import_lancedb in
[community.vectorstores](https://api.python.langchain.com/en/latest/vectorstores/langchain_community.vectorstores.lancedb.import_lancedb.html#langchain_community.vectorstores.lancedb.import_lancedb).
And we have core.utils.utils.guard_import that works exactly for this
purpose.
The import_<package> functions work inconsistently and rather be private
functions.
Change: replaced these functions with the guard_import function.

Related to #21133
2024-05-13 10:45:31 -04:00
ccurme
3003363605
langchain, community: remove cap on sqlalchemy and bump duckdb (#21509) 2024-05-13 10:16:09 -04:00
ccurme
01a3228d8e
standard tests: add test for few-shot examples (#21019) 2024-05-13 10:06:12 -04:00
David Duong
db22fcb58b
docs: style fixes for api reference docs (#21602)
- Make sure the left nav bar is horizontally scrollable 
- Make sure the navigation dropdown is vertically scrollable and height
capped at 80% of viewport height

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-05-13 06:49:50 -07:00
Chuyuan Qu
af875cff57
prompty: adding Microsoft langchain_prompty package (#21346)
Co-authored-by: Micky Liu <wayliu@microsoft.com>
Co-authored-by: wayliums <wayliums@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-05-11 04:03:44 +00:00
Erick Friis
56c6b5868b
infra: run codespell on v0.1 prs (#21545) 2024-05-10 12:51:42 -07:00
Matt Florence
d3ca2cc8c3
langchain: Fix broken OpenAIModerationChain and implement async (#18537)
Thank you for contributing to LangChain!

## PR title
lancghain[patch]: fix `OpenAIModerationChain` and implement async

## PR message
Description: fix `OpenAIModerationChain` and implement async

Issues: 
- https://github.com/langchain-ai/langchain/issues/18533 
- https://github.com/langchain-ai/langchain/issues/13685

Dependencies: none
Twitter handle: mattflo


## Add tests and docs
 
Existing documentation is broken:
https://python.langchain.com/docs/guides/safety/moderation


- [ 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: Emilia Katari <emilia@outpace.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
Co-authored-by: Erick Friis <erickfriis@gmail.com>
2024-05-10 19:04:13 +00:00
ccurme
4170e72a42
openai: fix loads unit test (#21542)
following changes to tests in core here:
https://github.com/langchain-ai/langchain/pull/21342/files
2024-05-10 18:46:34 +00:00
ccurme
d3ff9c5d6a
infra: turn off fail-fast for standard tests (#21541) 2024-05-10 18:28:57 +00:00
Erick Friis
e8efe8384d
docs: announcement bar dark mode 0.2 (#21540) 2024-05-10 10:13:02 -07:00