A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.
langchain[patch]: Release 0.2.11 (#24559)
langchain: globals fix (#21281)
all: add release notes to pypi (#24519)
ignore the first turn to apply "history" mechanism (#14118)
core,groq,openai,mistralai,robocorp,fireworks,anthropic[patch]: Update BaseModel subclass and instance checks to handle both v1 and proper namespaces (#24417)
[docs]: minor react change (#24509)
community[patch]: deprecate langchain_community Chroma in favor of langchain_chroma (#24474)
langchain: Copy libs/standard-tests folder when building devcontainer (#24470)
langchain[patch]: add async methods to ConversationSummaryBufferMemory (#20956)
langchain: Update ContextualCompressionRetriever base_retriever type to RetrieverLike (#24192)
langchain[patch]: Remove multiagent return_direct validation (#24419)
langchain-community==0.2.9
Changes since langchain-community==0.2.7
infra: add min version testing to pr test flow (#24358)
community[patch]: Release 0.2.9 (#24453)
community[patch]: gpt-4o-mini costs (#24421)
community[patch]: Force opt-in for WebResearchRetriever (CVE-2024-3095) (#24451)
community[minor]: [GoogleApiYoutubeLoader] Replace API used in _get_document_for_channel from search to playlistItem (#24034)
community[minor]: GraphCypherQAChain to accept additional inputs as provided by the user for cypher generation (#24300)
community[minor]: add mongodb byte store (#23876)
community[minor]: Add ability to specify file encoding and json encoding for FileChatMessageHistory (#24258)
Community[minor]: Added checksum in while send data to pebblo-cloud (#23968)
community[minor]: Add TextEmbed Embedding Integration (#22946)
community[minor]: Add Riza Python/JS code execution tool (#23995)
community[minor]: Add keybert-based link extractor (#24311)
community[minor]: GLiNER link extraction (#24314)
Mask API keys for various LLM/ChatModel Modules (#13885)
community[patch]: fix formatting (#24443)
Merge pull request #24315
Merge pull request #24363
Mask API key for ChatOpenAI based chat_models (#14293)
community: fix tool appending logic and update planner prompt in OpenAPI agent toolkit (#24384)
[fix] baidu qianfan AiMessage with usage_metadata (#24389)
community[minor]: [PebbloSafeLoader] Rename loader type and add SharePointLoader to supported loaders (#24393)
Community[patch]: Missing "stream" parameter in cloudflare_workersai (#23987)
community: support advanced text extraction options for pdf documents (#20265)
community[patch]: Release 0.2.8 (#24354)
community: Fix SQLDatabse.from_databricks issue when ran from Job (#24346)
Neo4j: Update with non-deprecated cypher methods, and new method to associate relationship embeddings (#23725)
docs: Add ChatBaichuan docstrings (#24348)
neo4j: Fix test for order-insensitive comparison and floating-point precision issues (#24338)
community[minor]: Add ApertureDB as a vectorstore (#24088)
community[patch]: Fix docstring for ollama parameter "keep_alive" (#23973)
community[patch]: Update TavilySearch to use TavilyClient instead of the deprecated Client (#24270)
baidu qianfan AiMessage with usage_metadata (#24288)
community[patch]: Release 0.2.10 (#24560)
community[patch]: small fixes to link extractors (#24528)
community[patch]: Update URL to the 2markdown API (#24546)
docs: Add RedisChatMessageHistory docstrings (#24548)
community[patch]: Remove targets_table from C* GraphVectorStore (#24502)
community[minor]: added new document loaders based on dedoc library (#24303)
community[minor]: add document transformer for extracting links (#24186)
all: add release notes to pypi (#24519)
core,groq,openai,mistralai,robocorp,fireworks,anthropic[patch]: Update BaseModel subclass and instance checks to handle both v1 and proper namespaces (#24417)
fix: load google credentials properly in GoogleDriveLoader (#12871)
community: sambanova integration minor changes (#24503)
community: Improve QianfanChatEndpoint tool result to model (#24466)
community[patch]: deprecate langchain_community Chroma in favor of langchain_chroma (#24474)
[Commutiy]: Prompts Fixed for ZERO_SHOT_REACT React Agent Type in create_sql_agent function (#23693)
[Vector Store] Fix function add_texts in TencentVectorDB (#24469)
community: add flag to toggle progress bar (#24463)
community: fix QianfanChatEndpoint default model (#24464)
docs: Add ChatSparkLLM docstrings (#24449)
langchain-community==0.2.9
Changes since langchain-community==0.2.7
infra: add min version testing to pr test flow (#24358)
community[patch]: Release 0.2.9 (#24453)
community[patch]: gpt-4o-mini costs (#24421)
community[patch]: Force opt-in for WebResearchRetriever (CVE-2024-3095) (#24451)
community[minor]: [GoogleApiYoutubeLoader] Replace API used in _get_document_for_channel from search to playlistItem (#24034)
community[minor]: GraphCypherQAChain to accept additional inputs as provided by the user for cypher generation (#24300)
community[minor]: add mongodb byte store (#23876)
community[minor]: Add ability to specify file encoding and json encoding for FileChatMessageHistory (#24258)
Community[minor]: Added checksum in while send data to pebblo-cloud (#23968)
community[minor]: Add TextEmbed Embedding Integration (#22946)
community[minor]: Add Riza Python/JS code execution tool (#23995)
community[minor]: Add keybert-based link extractor (#24311)
community[minor]: GLiNER link extraction (#24314)
Mask API keys for various LLM/ChatModel Modules (#13885)
community[patch]: fix formatting (#24443)
Merge pull request #24315
Merge pull request #24363
Mask API key for ChatOpenAI based chat_models (#14293)
community: fix tool appending logic and update planner prompt in OpenAPI agent toolkit (#24384)
[fix] baidu qianfan AiMessage with usage_metadata (#24389)
community[minor]: [PebbloSafeLoader] Rename loader type and add SharePointLoader to supported loaders (#24393)
Community[patch]: Missing "stream" parameter in cloudflare_workersai (#23987)
community: support advanced text extraction options for pdf documents (#20265)
community[patch]: Release 0.2.8 (#24354)
community: Fix SQLDatabse.from_databricks issue when ran from Job (#24346)
integrations[patch]: release model packages (#24900)
core[patch], integrations[patch]: convert TypedDict to tool schema support (#24641)
openai[patch]: openai proxy added to base embeddings (#24539)
langchain-openai==0.1.19
Changes since langchain-openai==0.1.17
integration releases (#24725)
openai[small]: Add the new model: gpt-4o-mini (#24594)
openai[patch]: move test (#24552)
standard-tests: add override check (#24407)
all: add release notes to pypi (#24519)
core,groq,openai,mistralai,robocorp,fireworks,anthropic[patch]: Update BaseModel subclass and instance checks to handle both v1 and proper namespaces (#24417)
openai: release 0.1.18 (#24369)
openai[patch]: use model_name in AzureOpenAI.ls_model_name (#24366)
langchain-openai==0.1.17
Changes since langchain-openai==0.1.16
openai: release 0.1.17 (#24361)
openai[patch]: fix key collision and _astream (#24345)
openai: raw response headers (#24150)
openai: remove some params from default serialization (#24280)
openai[patch]: update openai params (#23691)
Commits
c776471 community: fix AttributeError: 'YandexGPT' object has no attribute '_grpc_met...
752a71b integrations[patch]: release model packages (#24900)
1213a59 docs[patch]: Update kv store docs pages (#24848)
17a06cb infra: check templates based on integration (#24857)
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.
Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
- `@dependabot show ignore conditions` will show all of the ignore conditions of the specified dependency
- `@dependabot ignore major version` will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
- `@dependabot ignore minor version` will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
- `@dependabot ignore ` will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
- `@dependabot unignore ` will remove all of the ignore conditions of the specified dependency
- `@dependabot unignore ` will remove the ignore condition of the specified dependency and ignore conditions
Bumps the langchain group with 3 updates in the / directory: langchain, langchain-community and langchain-openai.
Updates
langchain
from 0.2.7 to 0.2.11Release notes
Sourced from langchain's releases.
... (truncated)
Commits
4919d5d
langchain[patch]: Release 0.2.11 (#24559)918e1c8
core[patch]: Release 0.2.23 (#24557)58def6e
Add tool calling example to Ollama ntbk (#24522)e787532
langchain:globals
fix (#21281)e80b093
community[patch]: small fixes to link extractors (#24528)9e06991
community[patch]: Update URL to the 2markdown API (#24546)a14e02a
core[patch]: Fix word spelling error inglobals.py
(#24532)378db2e
docs: Add RedisChatMessageHistory docstrings (#24548)a197a8e
openai[patch]: move test (#24552)0bb54ab
CI: Temporarily disable min version checking on pull request (#24551)Updates
langchain-community
from 0.2.7 to 0.2.10Release notes
Sourced from langchain-community's releases.
... (truncated)
Commits
8691a5a
community[patch]: Release 0.2.10 (#24560)4919d5d
langchain[patch]: Release 0.2.11 (#24559)918e1c8
core[patch]: Release 0.2.23 (#24557)58def6e
Add tool calling example to Ollama ntbk (#24522)e787532
langchain:globals
fix (#21281)e80b093
community[patch]: small fixes to link extractors (#24528)9e06991
community[patch]: Update URL to the 2markdown API (#24546)a14e02a
core[patch]: Fix word spelling error inglobals.py
(#24532)378db2e
docs: Add RedisChatMessageHistory docstrings (#24548)a197a8e
openai[patch]: move test (#24552)Updates
langchain-openai
from 0.1.16 to 0.1.20Release notes
Sourced from langchain-openai's releases.
Commits
c776471
community: fix AttributeError: 'YandexGPT' object has no attribute '_grpc_met...752a71b
integrations[patch]: release model packages (#24900)1213a59
docs[patch]: Update kv store docs pages (#24848)17a06cb
infra: check templates based on integration (#24857)a7380dd
cli: release 0.0.28 (#24852)e98e4be
cli: register new integration doc templates (#24854)210623b
core[minor]: Add support for pydantic 2 to utility to get fields (#24899)7d16940
core[patch]: Release 0.2.26 (#24898)add1611
community[patch]: Make the pydantic linter stricter (#24897)a4a444f
community[patch]: Fix arcee llm usage of root_validator(pre=False) (#24896)Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting
@dependabot rebase
.Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show