Commit Graph

8692 Commits

Author SHA1 Message Date
Jacob Lee
58a2123ca0 docs[patch]: Add missing redirects (#20076) 2024-04-05 12:54:00 -07:00
Eugene Yurtsev
520ff50adc community[patch]: Improve import callbacks to make it IDE friendly (#20050)
* declares __all__ as a list of strings (instead of dynamically
computing it)
* import type definitions when TYPE_CHECKING is true
2024-04-05 15:17:51 -04:00
Guangdong Liu
5a76087965 langchain-core[minor]: Allow passing local cache to language models (#19331)
After this PR it will be possible to pass a cache instance directly to a
language model. This is useful to allow different language models to use
different caches if needed.

- **Issue:** close #19276

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2024-04-05 11:19:54 -04:00
Eugene Yurtsev
e4fc0e7502 core[patch]: Document BaseCache abstraction in code (#20046)
Document the base cache abstraction in the cache.
2024-04-05 10:56:57 -04:00
Christophe Bornet
4d8a6a27a3 core[minor]: Implement aformat_prompt and ainvoke in BasePromptTemplate (#20035) 2024-04-05 10:36:43 -04:00
Christophe Bornet
7e5c1905b1 core[minor]: Add async aformat_document method (#20037) 2024-04-05 10:29:53 -04:00
Christophe Bornet
927793d088 Merge pull request #20038
* Implement aformat_messages for ChatMessagePromptTemplate
2024-04-05 10:25:27 -04:00
Erick Friis
ebd24bb5d6 docs: fix title cap (#20048) 2024-04-05 02:36:33 +00:00
Eugene Yurtsev
1ee8cf7b20 Docs: Update custom chat model (#19967)
* Clean up in the existing tutorial
* Add model_name to identifying params
* Add table to summarize messages
2024-04-04 22:36:03 -04:00
Erick Friis
5fc7bb01e9 docs: weaviate docs (#20042) 2024-04-04 19:01:02 -07:00
Bagatur
38fb1429fe docs: fix together model tab (#20032) 2024-04-04 15:33:43 -07:00
Jacob Lee
b69af26717 docs[patch]: Fix Model I/O quickstart (#20031)
@baskaryan
2024-04-04 15:28:58 -07:00
Usama Ahmed
94ac42c573 docs: fixing typo in argument name (#20028)
it's "mode" instead of "model", I fixed it
2024-04-04 22:28:28 +00:00
Bagatur
07eeeb84f3 docs: hide experimental anthropic (#20030) 2024-04-04 15:27:52 -07:00
Lance Martin
e76b9210dd Update example cookbook for Anthropic tool use (#20029) 2024-04-04 14:53:18 -07:00
Leonid Ganeline
3856dedff4 docs: integrations/providers update 9 (#19941)
- Added missed providers
- Added links, descriptions in related examples
- Formatted in a consistent format

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-04 21:37:48 +00:00
Bagatur
644ff46100 docs: mark anthropic tools wrapper as deprecated (#20024) 2024-04-04 21:33:55 +00:00
Leonid Ganeline
69bf6262aa docs: integrations/providers/unstructured update (#19892)
Updated a page with existing document loaders with links to examples.
Fixed formatting of one example.

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-04 21:31:27 +00:00
Bagatur
1b7ed6071a anthropic[patch]: Release 0.1.6 (#20026) 2024-04-04 14:29:50 -07:00
Bagatur
6860450e48 anthropic[patch]: use anthropic 0.23 (#20022) 2024-04-04 14:23:53 -07:00
Leonid Ganeline
4c969286fe docs integrations/providers update 10 (#19970)
Fixed broken links. Formatted to get consistent forms. Added missed
imports in the example code
2024-04-04 14:22:45 -07:00
Leonid Ganeline
82f0198be2 docs: graphs update (#19675)
Issue: The `graph` code was moved into the `community` package a long
ago. But the related documentation is still in the
[use_cases](https://python.langchain.com/docs/use_cases/graph/integrations/diffbot_graphtransformer)
section and not in the `integrations`.
Changes:
- moved the `use_cases/graph/integrations` notebooks into the
`integrations/graphs`
- renamed files and changed titles to follow the consistent format
- redirected old page URLs to new URLs in `vercel.json` and in several
other pages
- added descriptions and links when necessary
- formatted into the consistent format
2024-04-04 14:13:22 -07:00
Bagatur
be3dd62de4 anthropic[patch]: fix experimental tests (#20021) 2024-04-04 13:37:43 -07:00
Lance Martin
a6926772f0 Add cookbook for Anthropic .with_structured_output() (#20017) 2024-04-04 13:30:44 -07:00
Bagatur
86fdb79454 anthropic[patch]: bump core dep (#20019)
]
2024-04-04 13:28:23 -07:00
Bagatur
209de0a561 anthropic[minor]: tool use (#20016) 2024-04-04 13:22:48 -07:00
Leonid Ganeline
3aacd11846 community[minor]: added missed class to __all__ (#19888)
Added missed `UnstructuredCHMLoader` class to the
document_loader.\_\_init\_\_.py \_\_all\_\_
2024-04-04 16:16:51 -04:00
Jacob Lee
7f0cb3bfba docs[patch]: Make Docusaurus and Vercel add trailing slashes when navigating by default (#20014)
Should hopefully avoid weird broken link edge cases.

Relative links now trip up the Docusaurus broken link checker, so this
PR also removes them.

Also snuck in a small addition about asyncio
2024-04-04 12:49:15 -07:00
Chris Papademetrious
a954dedb77 langchain[minor]: enhance LocalFileStore to allow directory/file permissions to be specified (#18857)
**Description:**
The `LocalFileStore` class can be used to create an on-disk
`CacheBackedEmbeddings` cache. However, the default `umask` settings
gives file/directory write permissions only to the original user. Once
the cache directory is created by the first user, other users cannot
write their own cache entries into the directory.

To make the cache usable by multiple users, this pull request updates
the `LocalFileStore` constructor to allow the permissions for newly
created directories and files to be specified. The specified permissions
override the default `umask` values.

For example, when configured as follows:

```python
file_store = LocalFileStore(temp_dir, chmod_dir=0o770, chmod_file=0o660)
```

then "user" and "group" (but not "other") have permissions to access the
store, which means:

* Anyone in our group could contribute embeddings to the cache.
* If we implement cache cleanup/eviction in the future, anyone in our
group could perform the cleanup.

The default values for the `chmod_dir` and `chmod_file` parameters is
`None`, which retains the original behavior of using the default `umask`
settings.

**Issue:**
Implements enhancement #18075.

**Testing:**
I updated the `LocalFileStore` unit tests to test the permissions.

---------

Signed-off-by: chrispy <chrispy@synopsys.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2024-04-04 16:40:16 +00:00
Tomaz Bratanic
df25829f33 community[minor]: Add metadata filtering support for neo4j vector (#20001) 2024-04-04 11:37:06 -04:00
Ben Mitchell
b52b78478f community[minor]: Implement Async OpenSearch afrom_texts & afrom_embeddings (#20009)
- **Description:** Adds async variants of afrom_texts and
afrom_embeddings into `OpenSearchVectorSearch`, which allows for
`afrom_documents` to be called.
- **Issue:** I implemented this because my use case involves an async
scraper generating documents as and when they're ready to be ingested by
Embedding/OpenSearch
- **Dependencies:** None that I'm aware

Co-authored-by: Ben Mitchell <b.mitchell@reply.com>
2024-04-04 15:36:14 +00:00
Christophe Bornet
02152d3909 [docs][minor]: Fix typo in Custom Document Loader doc (#20003) 2024-04-04 10:59:33 -04:00
Jan Nissen
31e3ecc728 core[minor]: support pydantic V2 for JSONOutputParser, allow for other sources of JSON schemas (#19716)
This PR supports using Pydantic v2 objects to generate the schema for
the JSONOutputParser (#19441). This also adds a `json_schema` parameter
to allow users to pass any JSON schema to validate with, not just
pydantic.
2024-04-04 10:57:47 -04:00
Christophe Bornet
f97de4e275 core[minor]: Add aformat to FewShotPromptTemplate (#19652) 2024-04-04 10:24:55 -04:00
Utkarsha Gupte
b27f81c51c core[patch]: mypy ignore fixes #17048 (#19931)
core/langchain_core/_api[Patch]: mypy ignore fixes #17048
Related to #17048

Applied mypy fixes to below two files:
libs/core/langchain_core/_api/deprecation.py
libs/core/langchain_core/_api/beta_decorator.py

Summary of Fixes:
**Issue 1**
class _deprecated_property(type(obj)): # type: ignore
error: Unsupported dynamic base class "type"  [misc]
Fix: 
1. Added an __init__ method to _deprecated_property to initialize the
fget, fset, fdel, and __doc__ attributes.
2. In the __get__, __set__, and __delete__ methods, we now use the
self.fget, self.fset, and self.fdel attributes to call the original
methods after emitting the warning.

3. The finalize function now creates an instance of _deprecated_property
with the fget, fset, fdel, and doc attributes from the original obj
property.



**Issue 2**



 def finalize(  # type: ignore
                wrapper: Callable[..., Any], new_doc: str
            ) -> T:


error: All conditional function variants must have identical
signatures



Fix:
Ensured that both definitions of the finalize function have the
same signature

Twitter Handle -
https://x.com/gupteutkarsha?s=11&t=uwHe4C3PPpGRvoO5Qpm1aA
2024-04-04 10:22:38 -04:00
harry-cohere
e103492eb8 cohere: Add citations to agent, flexibility to tool parsing, fix SDK issue (#19965)
**Description:** Citations are the main addition in this PR. We now emit
them from the multihop agent! Additionally the agent is now more
flexible with observations (`Any` is now accepted), and the Cohere SDK
version is bumped to fix an issue with the most recent version of
pydantic v1 (1.10.15)
2024-04-04 07:02:30 -07:00
Jacob Lee
605c3f23e1 docs: reorg and visual refresh (#19765)
- put use cases in main sidebar
- move modules to own sidebar, rename components
- cleanup lcel section
- cleanup guides
- update font, cell highlighting

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-04 00:58:36 -07:00
Erick Friis
51bdfe04e9 groq: handle streaming tool call case (#19978) 2024-04-03 15:22:59 -07:00
Erick Friis
5acb564d6f groq: fix core version (#19976) 2024-04-03 14:49:57 -07:00
Erick Friis
9e60159043 groq: release 0.1.0 (#19975) 2024-04-03 14:41:48 -07:00
Graden Rea
88cf8a2905 groq: Add tool calling support (#19971)
**Description:** Add with_structured_output to groq chat models
**Issue:** 
**Dependencies:** N/A
**Twitter handle:** N/A
2024-04-03 14:40:20 -07:00
Eugene Yurtsev
6f20f140ca cli[minor]: Add disable sockets in unit tests (#19877) 2024-04-03 17:17:50 -04:00
Eugene Yurtsev
ea276d6547 docs: Custom Document Loaders (#19935)
Add information that shows how to create custom document loaders
2024-04-03 15:34:01 -04:00
Erick Friis
83f62fdacf core: fix try_load_from_hub for older langchain versions load_chain (#19964) 2024-04-03 17:00:25 +00:00
Tomaz Bratanic
09a0ecd000 langchain[minor]: Tests update metadata filtering examples of documents (#19963)
Removing metadata properties that are dicts as some databases don't
support that, and those properties aren't used in tests anyhow..
2024-04-03 12:44:14 -04:00
happy-go-lucky
c6432abdbe community[patch]: Implement delete method and all async methods in opensearch_vector_search (#17321)
- **Description:** In order to use index and aindex in
libs/langchain/langchain/indexes/_api.py, I implemented delete method
and all async methods in opensearch_vector_search
- **Dependencies:** No changes
2024-04-03 09:40:49 -07:00
Cheng, Penghui
cc407e8a1b community[minor]: weight only quantization with intel-extension-for-transformers. (#14504)
Support weight only quantization with intel-extension-for-transformers.
[Intel® Extension for
Transformers](https://github.com/intel/intel-extension-for-transformers)
is an innovative toolkit to accelerate Transformer-based models on Intel
platforms, in particular effective on 4th Intel Xeon Scalable processor
[Sapphire
Rapids](https://www.intel.com/content/www/us/en/products/docs/processors/xeon-accelerated/4th-gen-xeon-scalable-processors.html)
(codenamed Sapphire Rapids). The toolkit provides the below key
features:

* Seamless user experience of model compressions on Transformer-based
models by extending [Hugging Face
transformers](https://github.com/huggingface/transformers) APIs and
leveraging [Intel® Neural
Compressor](https://github.com/intel/neural-compressor)
* Advanced software optimizations and unique compression-aware runtime.
* Optimized Transformer-based model packages.
*
[NeuralChat](https://github.com/intel/intel-extension-for-transformers/blob/main/intel_extension_for_transformers/neural_chat),
a customizable chatbot framework to create your own chatbot within
minutes by leveraging a rich set of plugins and SOTA optimizations.
*
[Inference](https://github.com/intel/intel-extension-for-transformers/blob/main/intel_extension_for_transformers/llm/runtime/graph)
of Large Language Model (LLM) in pure C/C++ with weight-only
quantization kernels.
This PR is an integration of weight only quantization feature with
intel-extension-for-transformers.

Unit test is in
lib/langchain/tests/integration_tests/llm/test_weight_only_quantization.py
The notebook is in
docs/docs/integrations/llms/weight_only_quantization.ipynb.
The document is in
docs/docs/integrations/providers/weight_only_quantization.mdx.

---------

Signed-off-by: Cheng, Penghui <penghui.cheng@intel.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-03 16:21:34 +00:00
Eugene Yurtsev
d6d843ec24 langchain-postgres: Initial package with postgres chat history implementation (#19884)
- [x] Add in code examples for the chat message history class
- [ ] ~Add docs with notebook examples~ (can this be done later?)
- [x] Update README.md
2024-04-03 10:57:21 -04:00
Eugene Yurtsev
d293431e10 core[minor]: Add aload to document loader (#19936)
Add aload to document loader
2024-04-03 10:46:47 -04:00
Ángel Igareta
31a641a155 core: fix return of draw_mermaid_png and change to not save image by default (#19950)
- **Description:** Improvement for #19599: fixing missing return of
graph.draw_mermaid_png and improve it to make the saving of the rendered
image optional

Co-authored-by: Angel Igareta <angel.igareta@klarna.com>
2024-04-03 06:20:35 -07:00