Sourced from langchain's releases.
v0.1.4
What's Changed
- Minor nit on HyDE by
@rlancemartin
in langchain-ai/langchain#16478- template: fix azure params in retrieval agent by
@efriis
in langchain-ai/langchain#16257- cli[patch]: add integration tests to default makefile by
@efriis
in langchain-ai/langchain#16479- feat(llms): support more tasks in HuggingFaceHub LLM and remove deprecated dep by
@mspronesti
in langchain-ai/langchain#14406- Fixed typo on quickstart.ipynb by
@dudgeon
in langchain-ai/langchain#16482- community: SQLStrStore/SQLDocStore provide an easy SQL alternative to
InMemoryStore
to persist data remotely in a SQL storage by@gcheron
in langchain-ai/langchain#15909- community: Fix Baichuan Chat. by
@baichuan-assistant
in langchain-ai/langchain#15207- community: normalize bedrock embeddings by
@dmenini
in langchain-ai/langchain#15103- feat: adding paygo api support for Azure ML / Azure AI Studio by
@santiagxf
in langchain-ai/langchain#14560- community: Improve mlflow callback by
@serena-ruan
in langchain-ai/langchain#15691- Include scores in MongoDB Atlas QA chain results by
@NoahStapp
in langchain-ai/langchain#14666- langchain[patch]: In HTMLHeaderTextSplitter set default encoding to utf-8 by
@i-w-a
in langchain-ai/langchain#16372- langchain: Extract _aperform_agent_action from _aiter_next_step from AgentExecutor by
@gianfrancodemarco
in langchain-ai/langchain#15707- community:Adding Konko Completion endpoint by
@shivanimodi16
in langchain-ai/langchain#15570- docs: Updated integration docs structure for chat/anthropic by
@L-cloud
in langchain-ai/langchain#16268- Add KDBAI vector store by
@bu2kx
in langchain-ai/langchain#12797- Docs: Fix version in which astream_events was released by
@eyurtsev
in langchain-ai/langchain#16481- [langchain]: allow passing client with OpenAIAssistantRunnable by
@kristapratico
in langchain-ai/langchain#16486- community: Fix MlflowCallback with none artifacts_dir by
@serena-ruan
in langchain-ai/langchain#16487- langchain: Minor Fix: Enable Passing custom_headers for Authentication in GraphQL Agent/Tool by
@zendegani
in langchain-ai/langchain#16413- Feature: Add iFlyTek Spark LLM chat model support by
@vsxd
in langchain-ai/langchain#13389- community: Load list of files using UnstructuredFileLoader by
@raunakshrivastava7
in langchain-ai/langchain#16216- [community][cohere] Update cohere rerank and comparison docs by
@BeatrixCohere
in langchain-ai/langchain#16198- [community][document loaders][surrealdb] fix for asyncio by
@lalanikarim
in langchain-ai/langchain#16092- Community: added 'conversational' as a valid task for hugginface endopoint models by
@alessioserra
in langchain-ai/langchain#15761- Refactor: use SecretStr for yandex embedding by
@chyroc
in langchain-ai/langchain#15463- Remove double line by
@nfcampos
in langchain-ai/langchain#16426- community: avoid KeyError when language not in LANGUAGE_SEGMENTERS by
@dzlab
in langchain-ai/langchain#15212- community: Fix error message when litellm is not installed by
@jeremi
in langchain-ai/langchain#16316- docs: typo in tool use quickstart page by
@Tipwheal
in langchain-ai/langchain#16494- Docs: Add streaming section by
@eyurtsev
in langchain-ai/langchain#16468- added a few suggestions for sql docs by
@fpingham
in langchain-ai/langchain#16508- Update SQL agent toolkit docs by
@rlancemartin
in langchain-ai/langchain#16409- CI: Update issue template by
@eyurtsev
in langchain-ai/langchain#16517- docs: rm output by
@efriis
in langchain-ai/langchain#16519- CI: redirect feature requests to ideas in discussions by
@eyurtsev
in langchain-ai/langchain#16522- CI: more update to ideas template by
@eyurtsev
in langchain-ai/langchain#16524- langchain-google-vertexai: more verbose mypy config by
@jamesbraza
in langchain-ai/langchain#16307- Adds progress bar to VertexAIEmbeddings by
@ugm2
in langchain-ai/langchain#14542- docs:Updated integration docs structure for chat/google_vertex_ai_palm by
@manokhina
in langchain-ai/langchain#16201- CI: Fix ideas template by
@eyurtsev
in langchain-ai/langchain#16529- CI: more updates to feature request template by
@eyurtsev
in langchain-ai/langchain#16531- CI: Update q-a template by
@eyurtsev
in langchain-ai/langchain#16532- CI: more qa template changes by
@eyurtsev
in langchain-ai/langchain#16533- Updated comments about
n_gpu_layers
in the Metal section by@169
in langchain-ai/langchain#16501- Added a better error message when location is not supported by
@lkuligin
in langchain-ai/langchain#16535- community: VectorStore integration for SAP HANA Cloud Vector Engine by
@MartinKolbAtWork
in langchain-ai/langchain#16514- community: added support for Guardrails for Amazon Bedrock by
@harelix
in langchain-ai/langchain#15099
... (truncated)
5df8ab5
infra: move indexing documentation test (#16595)f3d61a6
langchain[patch]: Release 0.1.4 (#16592)61b2009
community[patch]: Release 0.0.16 (#16591)75ad0bb
openai[patch]: Release 0.0.4 (#16590)1e3ce33
core[patch]: Release 0.1.16 (#16589)6c89507
docs: add rag citations page (#16549)31790d1
openai[patch]: accept function_call dict in bind_functions (#16483)db80832
docs: output parser nits (#16588)ef42d9d
core[patch], community[patch], openai[patch]: consolidate openai tool…
(#16485)148347e
community[minor]: Add LiteLLM Router Integration (#15588)Sourced from weaviate-client's releases.
v4.4.0
What's Changed
- A new and improved client has been developed that:
- Streamlines the API and improves the UX when working with Weaviate
- Fully connects to Weaviate's new gRPC API for faster queries
- Ships with a fully autonomous dynamic batching algorithm for ease of data uploading
- Introduces strong typing of inputs and ouputs for Python-native safety
- Allows for the use of full typing hinting and generics to get the most out of your vectorised data
- See the documentation on the new features in the v4 client
- See the migration guide on how to upgrade from previous pre-release versions to this full release
- If you have troubles upgrading from v3 to v4 or find that your codebase no longer works upon the bump then please raise an issue on the board and we will see to it!
New Contributors
@halilbilgin
made their first contribution in weaviate/weaviate-python-client#422@trengrj
made their first contribution in weaviate/weaviate-python-client#468@mikewyer
made their first contribution in weaviate/weaviate-python-client#627@SavvasMohito
made their first contribution in weaviate/weaviate-python-client#705@jfrancoa
made their first contribution in weaviate/weaviate-python-client#763@daveatweaviate
made their first contribution in weaviate/weaviate-python-client#800Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.26.2...v4.4.0
Sourced from weaviate-client's changelog.
Version 4.4.0
This version is the first full release for the Python v4 client and requires weaviate versions >= 1.23.7.
Since the previous RC, there have been a number of improvements and final bug fixes.
- The type of
object.vector
has changed fromOptional[Dict[str, List[float]]]
toDict[str, List[float]]
so thatobject.vector
is neverNone
.- Exporting and importing of collections has been tidied up and improved.
- A number of methods have had input validation added to them.
- Most exceptions are now unified under a few common classes.
For more information around the new client, see here: https://weaviate.io/developers/weaviate/client-libraries/python
Version 4.4.rc1
This version is a release candidate for the python v4 client.
There is a significant breaking change in this version in anticipation of the named vectors functionality of future Weaviate versions.
- The
vector
property ofObject
has had its type changed fromOptional[List[float]]
toOptional[Dict[str, List[float]]]
.- Accessing of the vector property has changed from
object.vector
toobject.vector["default"]
.- When using the client with future releases, other named vectors will be accessible as
object.vector["name"]
.Newly created (as of 15:00UTC 01/30/24) WCS sandbox instances are now capable of handling gRPC connections and so the client has been updated accordingly in its
connect_to_wcs
method. If you are using an old sandbox, make a new one and use the new one instead.Minor bugfixes are also included.
Version 4.4.rc0
This version is a release candidate for the python v4 client.
All backward compatibility code is being removed and requires weaviate versions >= 1.23.5.
All deprecated code has been removed. Check the migration guide (https://www.weaviate.io/developers/weaviate/client-libraries/python#migration-guides) how to update your code.
Improvements include:
- Input validation
- Embedded weaviate shows an error when the chosen port(s) are already occupied
Fixes include:
- Filter chained references by reference count
- Various bug with filtered aggregation
- Aggregation with move to/away_from objects
- Timeouts also apply to GRPC calls
... (truncated)
8fa0241
Merge pull request #838
from weaviate/improve-coverage-106173cbc
remove needless pop39dc552
Merge pull request #837
from weaviate/v4-changelog6275ce4
reverse boolean logic for clarity1613066
remove try-finally354bed1
fix keyerrora59ca44
fix exporting config object into weaviate-compat dict1b9b18a
remove more code7012f9d
remove unused validation code1b5f86d
Add minimum version