Skip to content

Latest commit

 

History

History
2910 lines (1768 loc) · 180 KB

CHANGELOG.md

File metadata and controls

2910 lines (1768 loc) · 180 KB
Raw

Change Log

📣 Check out the releases page or the #announcements channel on the LangChain.dart Discord server for more details.

2024-09-25

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_supabase - v0.1.1+3
  • langchain_pinecone - v0.1.0+9
  • langchain_anthropic - v0.1.1+2
  • langchain_chroma - v0.2.1+3
  • langchain_mistralai - v0.2.3+1
  • vertex_ai - v0.1.0+2

langchain - v0.7.6

langchain_core - v0.3.6

langchain_community - v0.3.2

  • FEAT: Add support for deleteWhere in ObjectBoxVectorStore (#552). (90918bba)
  • REFACTOR: Add stubs for ObjectBox on web platform (#553). (41caed92)

langchain_firebase - v0.2.1+2

  • DOCS: Update Google's models in documentation (#551). (1da543f7)

langchain_google - v0.6.3+1

  • FEAT: Add support for reduced output dimensionality in GoogleGenerativeAIEmbeddings (#544). (d5880704)
  • DOCS: Update Google's models in documentation (#551). (1da543f7)

langchain_ollama - v0.3.2

  • FEAT: Update Ollama default model to llama-3.2 (#554). (f42ed0f0)

langchain_openai - v0.7.2

  • FEAT: Add OpenAI o1-preview and o1-mini to model catalog (#555). (9ceb5ff9)
  • REFACTOR: Migrate ChatOpenAI to maxCompletionTokens (#557). (08057a5b)

ollama_dart - v0.2.2

  • FEAT: Update Ollama default model to llama-3.2 (#554). (f42ed0f0)

openai_dart - v0.4.2

  • FEAT: Add OpenAI o1-preview and o1-mini to model catalog (#555). (9ceb5ff9)
  • FEAT: Add support for maxCompletionTokens and reasoningTokens in openai_dart (#556). (37d75b61)
  • FEAT: Option to include file search results in assistants API (#543). (e916ad3c)

2024-08-22

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_firebase - v0.2.1+1
  • langchain_supabase - v0.1.1+2
  • langchain_pinecone - v0.1.0+8
  • langchain_anthropic - v0.1.1+1
  • langchain_chroma - v0.2.1+2

langchain - v0.7.5

  • FEAT: Add ToolsAgent for models with tool-calling support (#530). (f3ee5b44)
  • FEAT: Deprecate OpenAIToolsAgent in favour of ToolsAgent (#532). (68d8011a)
  • DOCS: Add Code Assist AI in README and documentation (#538). (e752464c)

langchain_core - v0.3.5

  • FEAT: Add copyWith method to all RunnableOptions subclasses (#531). (42c8d480)
  • FEAT: Support OpenAI's strict mode for tool calling in ChatOpenAI (#536). (71623f49)
  • FEAT: Deprecate OpenAIToolsAgent in favour of ToolsAgent (#532). (68d8011a)

langchain_community - v0.3.1

  • FEAT: Deprecate OpenAIToolsAgent in favour of ToolsAgent (#532). (68d8011a)

langchain_openai - v0.7.1

  • FEAT: Add support for Structured Outputs in ChatOpenAI (#526). (c5387b5d)
  • FEAT: Handle refusal in OpenAI's Structured Outputs API (#533). (f4c4ed99)
  • FEAT: Include logprobs in result metadata from ChatOpenAI (#535). (1834b3ad)
  • FEAT: Add chatgpt-4o-latest to model catalog (#527). (ec82c760)
  • FEAT: Add gpt-4o-2024-08-06 to model catalog (#522). (563200e0)
  • FEAT: Deprecate OpenAIToolsAgent in favour of ToolsAgent (#532). (68d8011a)
  • REFACTOR: Don't send OpenAI-Beta header in ChatOpenAI (#511). (0e532bab)

langchain_ollama - v0.3.1

  • FEAT: Add support for min_p in Ollama (#512). (e40d54b2)
  • FEAT: Add copyWith method to all RunnableOptions subclasses (#531). (42c8d480)

langchain_google - v0.6.2

  • FEAT: Add copyWith method to all RunnableOptions subclasses (#531). (42c8d480)

langchain_mistralai - v0.2.3

  • FEAT: Add copyWith method to all RunnableOptions subclasses (#531). (42c8d480)

openai_dart - v0.4.1

  • FEAT: Add support for Structured Outputs (#525). (c7574077)
  • FEAT: Add log probabilities for refusal tokens (#534). (8470a24c)
  • FEAT: Add gpt-4o-2024-08-06 to model catalog (#522). (563200e0)
  • FEAT: Add chatgpt-4o-latest to model catalog (#527). (ec82c760)

ollama_dart - v0.2.1

2024-07-26

Changes

Packages with breaking changes:

Packages with other changes:

langchain - v0.7.4

  • FEAT: Add Fallback support for Runnables (#501). (5887858d)
  • FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
  • REFACTOR: Remove default model from the language model options (#498). (44363e43)
  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)
  • DOCS: Update README.md with Ollama tool call support. (e016b0bd)

langchain_core - v0.3.4

  • FEAT: Add Fallback support for Runnables (#501). (5887858d)
  • FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
  • REFACTOR: Remove default model from the language model options (#498). (44363e43)

langchain_community - v0.3.0

  • FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

langchain_ollama - v0.3.0

  • FEAT: Add tool calling support in ChatOllama (#505). (6ffde204)
  • BREAKING FEAT: Update Ollama default model to llama-3.1 (#506). (b1134bf1)
  • FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
  • REFACTOR: Remove default model from the language model options (#498). (44363e43)
  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)
  • DOCS: Update Ollama request options default values in API docs (#479). (e1f93366)

langchain_openai - v0.7.0

  • BREAKING FEAT: Update ChatOpenAI default model to gpt-4o-mini (#507). (c7b8ce91)
  • FEAT: Add support for disabling parallel tool calls in ChatOpenAI (#493). (c46d676d)
  • FEAT: Add GPT-4o-mini to model catalog (#497). (faa23aee)
  • FEAT: Add support for service tier in ChatOpenAI (#495). (af79a4ff)
  • FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
  • REFACTOR: Remove default model from the language model options (#498). (44363e43)
  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

langchain_anthropic - v0.1.1

  • FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
  • REFACTOR: Remove default model from the language model options (#498). (44363e43)
  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

langchain_firebase - v0.2.1

  • FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
  • REFACTOR: Remove default model from the language model options (#498). (44363e43)
  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

langchain_google - v0.6.1

  • FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
  • REFACTOR: Remove default model from the language model options (#498). (44363e43)
  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

langchain_mistralai - v0.2.2

  • FEAT: Implement additive options merging for cascade bind calls (#500). (8691eb21)
  • REFACTOR: Remove default model from the language model options (#498). (44363e43)
  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

langchain_chroma - v0.2.1+1

  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

langchain_pinecone - v0.1.0+7

  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

langchain_supabase - v0.1.1+1

  • REFACTOR: Depend on exact versions for internal 1st party dependencies (#484). (244e5e8f)

ollama_dart - v0.2.0

  • FEAT: Add tool calling support in ollama_dart (#504). (1ffdb41b)
  • BREAKING FEAT: Update Ollama default model to llama-3.1 (#506). (b1134bf1)
  • FEAT: Add support for Ollama version and model info (#488). (a110ecb7)
  • FEAT: Add suffix support in Ollama completions API in ollama_dart (#503). (30d05a69)
  • BREAKING REFACTOR: Change Ollama push model status type from enum to String (#489). (90c9ccd9)
  • DOCS: Update Ollama request options default values in API docs (#479). (e1f93366)

openai_dart - v0.4.0

  • FEAT: Add support for disabling parallel tool calls in openai_dart (#492). (a91e0719)
  • FEAT: Add GPT-4o-mini to model catalog (#497). (faa23aee)
  • FEAT: Support chunking strategy in file_search tool in openai_dart (#496). (cfa974a9)
  • FEAT: Add support for overrides in the file search tool in openai_dart (#491). (89605638)
  • FEAT: Allow to customize OpenAI-Beta header in openai_dart (#502). (5fed8dbb)
  • FEAT: Add support for service tier in openai_dart (#494). (0838e4b9)

2024-07-02

Changes

New packages:

Packages with breaking changes:

Packages with other changes:

langchain - v0.7.3

Note: Anthropic integration (ChatAnthropic) is available in the new langchain_anthropic package.

  • FEAT: Add support for TavilySearchResultsTool and TavilyAnswerTool (#467). (a9f35755)
  • DOCS: Document existing integrations in README.md. (cc4246c8)

langchain_core - v0.3.3

  • FEAT: Add support for ChatToolChoiceRequired (#474). (bf324f36)
  • FEAT: Update ChatResult.id concat logic (#477). (44c7fafd)

langchain_community - v0.2.2

  • FEAT: Add support for TavilySearchResultsTool and TavilyAnswerTool (#467). (a9f35755)

langchain_anthropic - v0.1.0

langchain_firebase - v0.2.0

Note: ChatFirebaseVertexAI now uses gemini-1.5-flash model by default.

  • BREAKING FEAT: Update ChatFirebaseVertexAI default model to gemini-1.5-flash (#458). (d3c96c52)
  • FEAT: Add support for ChatToolChoiceRequired (#474). (bf324f36)
  • FEAT: Support response MIME type in ChatFirebaseVertexAI (#461) (#463). (c3452721)
  • FEAT: Add support for Firebase Auth in ChatFirebaseVertexAI (#460). (6d137290)
  • FEAT: Add support for usage metadata in ChatFirebaseVertexAI (#457). (2587f9e2)
  • REFACTOR: Simplify how tools are passed to the internal Firebase client (#459). (7f772396)

langchain_google - v0.6.0

Note: ChatGoogleGenerativeAI now uses gemini-1.5-flash model by default.

  • BREAKING FEAT: Update ChatGoogleGenerativeAI default model to gemini-1.5-flash (#462). (c8b30c90)
  • FEAT: Add support for ChatToolChoiceRequired (#474). (bf324f36)
  • FEAT: Support response MIME type and schema in ChatGoogleGenerativeAI (#461). (e258399e)
  • REFACTOR: Migrate conditional imports to js_interop (#453). (a6a78cfe)

langchain_openai - v0.6.3

  • FEAT: Add support for ChatToolChoiceRequired (#474). (bf324f36)

langchain_ollama - v0.2.2+1

  • DOCS: Update ChatOllama API docs. (cc4246c8)

langchain_chroma - v0.2.1

  • Update a dependency to the latest release.

langchain_mistralai - v0.2.1

  • Update a dependency to the latest release.

langchain_pinecone - v0.1.0+6

  • Update a dependency to the latest release.

langchain_supabase - v0.1.1

  • Update a dependency to the latest release.

anthropic_sdk_dart - v0.1.0

  • FEAT: Add support for tool use in anthropic_sdk_dart client (#469). (81896cfd)
  • FEAT: Add extensions on ToolResultBlockContent in anthropic_sdk_dart (#476). (8d92d9b0)
  • REFACTOR: Improve schemas names in anthropic_sdk_dart (#475). (8ebeacde)
  • REFACTOR: Migrate conditional imports to js_interop (#453). (a6a78cfe)

ollama_dart - v0.1.2

  • FEAT: Add support for listing running Ollama models (#451). (cfaa31fb)
  • REFACTOR: Migrate conditional imports to js_interop (#453). (a6a78cfe)

tavily_dart - v0.1.0

  • FEAT: Implement tavily_dart, a Dart client for Tavily API (#456). (fbfb79ba)

googleai_dart - v0.1.0+2

  • REFACTOR: Migrate conditional imports to js_interop (#453). (a6a78cfe)

mistralai_dart - v0.0.3+3

  • REFACTOR: Migrate conditional imports to js_interop (#453). (a6a78cfe)

openai_dart - v0.3.3+1

  • REFACTOR: Migrate conditional imports to js_interop (#453). (a6a78cfe)

2024-06-01

Changes

New packages:

Packages with other changes:

langchain - v0.7.2

langchain_core - v0.3.2

  • FEAT: Add Runnable.close() to close any resources associated with it (#439). (4e08cced)
  • FIX: Stream errors are not propagated by StringOutputParser (#440). (496b11cc)

langchain_community - v0.2.1

langchain_openai - v0.6.2

  • DOCS: Document tool calling with OpenRouter (#437). (47986592)

anthropic_sdk_dart - v0.0.1

  • FEAT: Implement anthropic_sdk_dart, a Dart client for Anthropic API (#433). (e5412b)

ollama_dart - v0.1.1

  • FEAT: Support buffered stream responses (#445). (ce2ef30c)

openai_dart - v0.3.3

  • FEAT: Support FastChat OpenAI-compatible API (#444). (ddaf1f69)
  • FIX: Make vector store name optional (#436). (29a46c7f)
  • FIX: Fix deserialization of sealed classes (#435). (7b9cf223)

2024-05-20

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_ollama - v0.2.1+1
  • langchain_openai - v0.6.1+1

openai_dart - v0.3.2+1

  • FIX: Rename CreateRunRequestModel factories names (#429). (fd15793b)
  • FIX: Make quote nullable in MessageContentTextAnnotationsFileCitation (#428). (75b95645)

ollama_dart - v0.1.0+1

  • FIX: digest path param in Ollama blob endpoints (#430). (2e9e935a)

langchain_firebase - v0.1.0+1

  • DOCS: Fix lint issues in langchain_firebase example. (f85a6ad7)

2024-05-14

Changes

Packages with breaking changes:

Packages with other changes:

langchain - v0.7.1

Note: VertexAI for Firebase (ChatFirebaseVertexAI) is available in the new langchain_firebase package.

langchain_core - v0.3.1

langchain_community - v0.2.0+1

  • Update a dependency to the latest release.

langchain_google - v0.5.0

Note: ChatGoogleGenerativeAI and GoogleGenerativeAIEmbeddings now use the version v1beta of the Gemini API (instead of v1) which support the latest models (gemini-1.5-pro-latest and gemini-1.5-flash-latest).

VertexAI for Firebase (ChatFirebaseVertexAI) is available in the new langchain_firebase package.

  • FEAT: Add support for tool calling in ChatGoogleGenerativeAI (#419). (df41f38a)
  • DOCS: Add Gemini 1.5 Flash to models list (#423). (40f4c9de)
  • BREAKING FEAT: Migrate internal client from googleai_dart to google_generative_ai (#407). (fa4b5c37)

langchain_firebase - v0.1.0

  • FEAT: Add support for ChatFirebaseVertexAI (#422). (8d0786bc)
  • DOCS: Add Gemini 1.5 Flash to models list (#423). (40f4c9de)

langchain_openai - v0.6.1

  • FEAT: Add GPT-4o to model catalog (#420). (96214307)
  • FEAT: Include usage stats when streaming with OpenAI and ChatOpenAI (#406). (5e2b0ecc)

langchain_ollama - v0.2.1

  • FEAT: Handle finish reason in ChatOllama (#416). (a5e1af13)
  • FEAT: Add keepAlive option to OllamaEmbeddings (#415). (32e19028)
  • FEAT: Update Ollama default model from llama2 to llama3 (#417). (9d30b1a1)
  • REFACTOR: Remove deprecated Ollama options (#414). (861a2b74)

openai_dart - v0.3.2

  • FEAT: Add GPT-4o to model catalog (#420). (96214307)
  • FEAT: Add support for different content types in Assistants API and other fixes (#412). (97acab45)
  • FEAT: Add support for completions and embeddings in batch API in openai_dart (#425). (16fe4c68)
  • FEAT: Add incomplete status to RunObject in openai_dart (#424). (71b116e6)

ollama_dart - v0.1.0

  • BREAKING FEAT: Align Ollama client to the Ollama v0.1.36 API (#411). (326212ce)
  • FEAT: Update Ollama default model from llama2 to llama3 (#417). (9d30b1a1)
  • FEAT: Add support for done reason (#413). (cc5b1b02)

googleai_dart - v0.1.0

langchain_chroma - v0.2.0+4

  • Update a dependency to the latest release.

langchain_mistralai - v0.2.0+1

  • Update a dependency to the latest release.

langchain_pinecone - v0.1.0+4

  • Update a dependency to the latest release.

langchain_supabase - v0.1.0+4

  • Update a dependency to the latest release.

2024-05-09

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_openai - v0.6.0+2

openai_dart - v0.3.1

  • FEAT: Add support for stream_options in openai_dart (#405). (c15714ca)
  • FIX: RunStepDetailsToolCalls deserialization in Assistants API v2 (#404). (d76c6aba)

2024-05-06

Changes

Packages with breaking changes:

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_openai - v0.6.0+1

openai_dart - v0.3.0

  • BREAKING FEAT: Migrate OpenAI Assistants API to v2 and add support for vector stores (#402). (45de29a1)
  • FEAT: Add support for ChatCompletionToolChoiceMode.required (#402). (45de29a1)

2024-05-05

Changes

Packages with breaking changes:

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_supabase - v0.1.0+3
  • langchain_pinecone - v0.1.0+3
  • langchain_chroma - v0.2.0+3

langchain - v0.7.0

  • BREAKING FEAT: Migrate from function calling to tool calling (#400). (44413b83)
  • BREAKING REFACTOR: Improve Tool abstractions (#398). (2a50aec2)

langchain_core - v0.3.0

  • BREAKING FEAT: Migrate from function calling to tool calling (#400). (44413b83)
  • BREAKING REFACTOR: Improve Tool abstractions (#398). (2a50aec2)

langchain_community - v0.2.0

  • BREAKING FEAT: Migrate from function calling to tool calling (#400). (44413b83)
  • BREAKING REFACTOR: Improve Tool abstractions (#398). (2a50aec2)

langchain_openai - v0.6.0

  • BREAKING FEAT: Migrate from function calling to tool calling (#400). (44413b83)
  • BREAKING REFACTOR: Improve Tool abstractions (#398). (2a50aec2)

langchain_google - v0.4.0

  • BREAKING FEAT: Migrate from function calling to tool calling (#400). (44413b83)

langchain_mistralai - v0.2.0

  • BREAKING FEAT: Migrate from function calling to tool calling (#400). (44413b83)

langchain_ollama - v0.2.0

  • BREAKING FEAT: Migrate from function calling to tool calling (#400). (44413b83)

2024-04-30

Changes

Packages with breaking changes:

Packages with other changes:

Packages with dependency updates only:

  • langchain_community - v0.1.0+2
  • langchain_ollama - v0.1.0+2
  • langchain_supabase - v0.1.0+2
  • langchain_pinecone - v0.1.0+2
  • langchain_chroma - v0.2.0+2
  • langchain_google - v0.3.0+2
  • langchain_mistralai - v0.1.0+2

langchain - v0.6.0+1

  • FEAT Add support for RunnableRouter (#386). (827e262)
  • FEAT: Add support for Runnable.mapInputStream (#393). (a2b6bbb5)
  • FEAT: Add support for JsonOutputParser (#392). (c6508f0f)
  • FEAT: Reduce input stream for PromptTemplate, LLM, ChatModel, Retriever and Tool (#388). (b59bcd40)
  • BREAKING FEAT: Support different logic for streaming in RunnableFunction (#394). (8bb2b8ed)
  • FIX: Allow async functions in Runnable.mapInput (#396). (e4c35092)
  • DOCS: Update LangChain Expression Language documentation (#395). (6ce75e5f)

langchain_core - v0.2.0+1

  • FEAT Add support for RunnableRouter (#386). (827e262)
  • FEAT: Add support for Runnable.mapInputStream (#393). (a2b6bbb5)
  • FEAT: Add support for JsonOutputParser (#392). (c6508f0f)
  • FEAT: Reduce input stream for PromptTemplate, LLM, ChatModel, Retriever and Tool (#388). (b59bcd40)
  • BREAKING FEAT: Support different logic for streaming in RunnableFunction (#394). (8bb2b8ed)
  • FIX: Allow async functions in Runnable.mapInput (#396). (e4c35092)

langchain_openai - v0.5.1+1

  • FEAT: Add support for Runnable.mapInputStream (#393). (a2b6bbb5)

openai_dart - v0.2.2

  • FEAT: Add temperature, top_p and response format to Assistants API (#384). (1d18290f)

2024-04-16

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_openai - v0.5.0+1

langchain - v0.5.0+1

openai_dart - v0.2.1

  • FEAT: Add support for Batch API in openai_dart (#383). (6b89f4a2)
  • FEAT: Support specifying tool choice in Assistant API in openai_dart (#382). (97d7977a)
  • FEAT: Support JSON mode in Assistant API in openai_dart (#381). (a864dae3)
  • FEAT: Support max tokens and truncation strategy in Assistant API in openai_dart (#380). (7153167b)
  • FEAT: Add streaming support to Assistant API in openai_dart (#379). (6ef68196)
  • FEAT: Update models catalog with GPT-4 Turbo with Vision in openai_dart (#378). (88537540)
  • FEAT: Add Weights & Biases fine-tuning integration and seed in openai_dart (#377). (a5fff1bf)
  • FEAT: Add support for checkpoints in fine-tuning jobs in openai_dart (#376). (69f8e2f9)

2024-04-10

Changes

Packages with breaking changes:

Packages with other changes:

langchain - v0.5.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)
  • BREAKING REFACTOR: Simplify LLMResult and ChatResult classes (#363). (ffe539c1)
  • BREAKING REFACTOR: Simplify Output Parsers (#367). (f24b7058)
  • BREAKING REFACTOR: Remove deprecated generate and predict APIs (#335). (c55fe50f)
  • REFACTOR: Simplify internal .stream implementation (#364). (c83fed22)
  • FEAT: Implement .batch support (#370). (d254f929)
  • FEAT: Add reduceOutputStream option to StringOutputParser (#368). (7f9a9fae)
  • DOCS: Update LCEL docs. (ab3ab573)
  • DOCS: Add RAG example using OllamaEmbeddings and ChatOllama (#337). (8bddc6c0)

langchain_community - v0.1.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)

langchain_core - v0.1.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)
  • BREAKING REFACTOR: Simplify LLMResult and ChatResult classes (#363). (ffe539c1)
  • BREAKING REFACTOR: Simplify Output Parsers (#367). (f24b7058)
  • REFACTOR: Simplify internal .stream implementation (#364). (c83fed22)
  • FEAT: Implement .batch support (#370). (d254f929)
  • FEAT: Add reduceOutputStream option to StringOutputParser (#368). (7f9a9fae)

langchain_chroma - v0.2.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)

langchain_google - v0.3.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)
  • BREAKING REFACTOR: Simplify LLMResult and ChatResult classes (#363). (ffe539c1)
  • BREAKING REFACTOR: Simplify Output Parsers (#367). (f24b7058)
  • BREAKING REFACTOR: Remove deprecated generate and predict APIs (#335). (c55fe50f)
  • REFACTOR: Simplify internal .stream implementation (#364). (c83fed22)
  • FEAT: Implement .batch support (#370). (d254f929)
  • FEAT: Add streaming support in ChatGoogleGenerativeAI (#360). (68bfdb04)
  • FEAT: Support tuned models in ChatGoogleGenerativeAI (#359). (764b633d)
  • FEAT: Add support for GoogleGenerativeAIEmbeddings (#362). (d4f888a0)
  • FEAT: Support output dimensionality in GoogleGenerativeAIEmbeddings (#373). (6dcb27d8)
  • FEAT: Support updating API key in Google AI client (#357). (b9b808e7)

langchain_mistralai - v0.1.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)
  • BREAKING REFACTOR: Simplify LLMResult and ChatResult classes (#363). (ffe539c1)
  • BREAKING REFACTOR: Simplify Output Parsers (#367). (f24b7058)
  • BREAKING REFACTOR: Remove deprecated generate and predict APIs (#335). (c55fe50f)
  • REFACTOR: Simplify internal .stream implementation (#364). (c83fed22)
  • FEAT: Implement .batch support (#370). (d254f929)

langchain_ollama - v0.1.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)
  • BREAKING REFACTOR: Simplify LLMResult and ChatResult classes (#363). (ffe539c1)
  • BREAKING REFACTOR: Simplify Output Parsers (#367). (f24b7058)
  • BREAKING REFACTOR: Remove deprecated generate and predict APIs (#335). (c55fe50f)
  • REFACTOR: Simplify internal .stream implementation (#364). (c83fed22)
  • FEAT: Implement .batch support (#370). (d254f929)

langchain_openai - v0.5.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)
  • BREAKING REFACTOR: Simplify LLMResult and ChatResult classes (#363). (ffe539c1)
  • BREAKING REFACTOR: Simplify Output Parsers (#367). (f24b7058)
  • BREAKING REFACTOR: Remove deprecated generate and predict APIs (#335). (c55fe50f)
  • REFACTOR: Simplify internal .stream implementation (#364). (c83fed22)
  • FEAT: Implement .batch support (#370). (d254f929)
  • FEAT: Remove deprecated OpenAI instance id (#350). (52939336)

langchain_pinecone - v0.1.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)

langchain_supabase - v0.1.0

  • BREAKING REFACTOR: Introduce langchain_core and langchain_community packages (#328). (5fa520e6)

chromadb - v0.2.0

  • FIX: Have the == implementation use Object instead of dynamic (#334). (89f7b0b9)

openai_dart - v0.2.0

  • FEAT: Sync OpenAI API (#347). (f296eef6)
  • FIX: Have the == implementation use Object instead of dynamic (#334). (89f7b0b9)

vertex_ai - v0.1.0

googleai_dart - v0.0.4

  • FEAT: Support generateContent for tuned model in googleai_dart client (#358). (b4641a09)
  • FEAT: Support output dimensionality in Google AI Embeddings (#373). (6dcb27d8)
  • FEAT: Support updating API key in Google AI client (#357). (b9b808e7)
  • FIX: Have the == implementation use Object instead of dynamic (#334). (89f7b0b9)

mistralai_dart - v0.0.3+1

  • FIX: Have the == implementation use Object instead of dynamic (#334). (89f7b0b9)

ollama_dart - v0.0.3+1

  • FIX: Have the == implementation use Object instead of dynamic (#334). (89f7b0b9)

2024-02-15

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

googleai_dart - v0.0.3

  • FEAT: Add streaming support to googleai_dart client (#299). (2cbd538a)
  • FEAT: Update meta and test dependencies (#331). (912370ee)
  • DOCS: Update pubspecs. (d23ed89a)

openai_dart - v0.1.7

langchain_openai - v0.4.1

ollama_dart - v0.0.3

  • FEAT: Add Ollama keep_alive param to control how long models stay loaded (#319). (3b86e227)
  • FEAT: Update meta and test dependencies (#331). (912370ee)
  • DOCS: Update pubspecs. (d23ed89a)

langchain_ollama - v0.0.4

  • FEAT: Add Ollama keep_alive param to control how long models stay loaded (#319). (3b86e227)
  • FEAT: Update meta and test dependencies (#331). (912370ee)
  • DOCS: Update pubspecs. (d23ed89a)

chromadb - v0.1.2

  • FEAT: Update meta and test dependencies (#331). (912370ee)

langchain - v0.4.2

  • FEAT: Update meta and test dependencies (#331). (912370ee)

langchain_chroma - v0.1.1

langchain_google - v0.2.4

langchain_mistralai - v0.0.3

langchain_pinecone - v0.0.7

langchain_supabase - v0.0.1+1

mistralai_dart - v0.0.3

vertex_ai - v0.0.10

2024-01-31

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

langchain - v0.4.1

langchain_supabase - v0.0.1

  • FEAT: Add support for Supabase VectorStore (#69). (be9e72bc)

langchain_chroma - v0.1.0+15

langchain_google - v0.2.3+3

langchain_mistralai - v0.0.2+3

langchain_ollama - v0.0.3+3

langchain_openai - v0.4.0+1

langchain_pinecone - v0.0.6+14

chromadb - v0.1.1+1

googleai_dart - v0.0.2+2

mistralai_dart - v0.0.2+3

ollama_dart - v0.0.2+1

openai_dart - v0.1.6+1

vertex_ai - v0.0.9+1

2024-01-26

Changes

Packages with breaking changes:

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_ollama - v0.0.3+2
  • langchain_mistralai - v0.0.2+2
  • langchain_pinecone - v0.0.6+13
  • langchain_chroma - v0.1.0+14
  • langchain_google - v0.2.3+2

langchain - v0.4.0

langchain_openai - v0.4.0

  • BREAKING FEAT: Update OpenAIEmbeddings' default model to text-embedding-3-small (#313). (43463481)
  • FEAT: Add support for shortening embeddings in OpenAIEmbeddings (#312). (5f5eb54f)

openai_dart - v0.1.6

  • FEAT: Add gpt-4-0125-preview and gpt-4-turbo-preview in model catalog (#309). (f5a78867)
  • FEAT: Add text-embedding-3-small and text-embedding-3-large in model catalog (#310). (fda16024)
  • FEAT: Add support for shortening embeddings (#311). (c725db0b)

2024-01-25

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

langchain_openai - v0.3.3+1

  • FIX: Specified model is always overwritten in OpenAIFunctionsAgent (#308). (32dc37d8)
  • DOCS: Update docs. (6f15d7f8)

2024-01-20

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_pinecone - v0.0.6+12
  • langchain_ollama - v0.0.3+1
  • langchain_chroma - v0.1.0+13

langchain - v0.3.3

  • DOCS: Add Anyscale and Together AI documentation (#305). (7daa3eb0)

langchain_openai - v0.3.3

  • FEAT: Support Anyscale in ChatOpenAI and OpenAIEmbeddings wrappers (#305). (7daa3eb0)
  • FEAT: Support Together AI in ChatOpenAI wrapper (#297). (28ab56af)
  • FEAT: Support Together AI in OpenAIEmbeddings wrapper (#304). (ddc761d6)

langchain_google - v0.2.3+1

  • REFACTOR: Remove tiktoken in favour of countTokens API on VertexAI (#307). (8158572b)

langchain_mistralai - v0.0.2+1

  • REFACTOR: Update safe_mode and max temperature in Mistral chat (#300). (1a4ccd1e)

openai_dart - v0.1.5

  • FEAT: Support Anyscale API in openai_dart client (#303). (e0a3651c)
  • FEAT: Support Together AI API (#296). (ca6f23d5)
  • FEAT: Support Together AI Embeddings API in openai_dart client (#301). (4a6e1045)
  • FEAT: Add usage to Run/RunStep in openai_dart client (#302). (cc6538b5)

vertex_ai - v0.0.9

  • FEAT: Add count tokens method to vertex_ai client (#306). (54ae317d)

mistralai_dart - v0.0.2+2

  • REFACTOR: Update safe_mode and max temperature in Mistral chat (#300). (1a4ccd1e)

2024-01-13

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_pinecone - v0.0.6+11
  • langchain_chroma - v0.1.0+12

langchain - v0.3.2

  • REFACTOR: Make all LLM options fields nullable and add copyWith (#284). (57eceb9b)
  • FIX: Export ConversationSummaryMemory (#283). (76b01d23)
  • FEAT: Update internal dependencies (#291). (69621cc6)

langchain_openai - v0.3.2

  • FEAT: Support OpenRouter API in ChatOpenAI wrapper (#292). (c6e7e5be) (docs)
  • REFACTOR: Make all LLM options fields nullable and add copyWith (#284). (57eceb9b)
  • REFACTOR: Migrate tokenizer to langchain_tiktoken package (#285). (6a3b6466)
  • FEAT: Update internal dependencies (#291). (69621cc6)

langchain_google - v0.2.3

  • REFACTOR: Use cl100k_base encoding model when no tokenizer is available (#295). (ca908e80)
  • REFACTOR: Make all LLM options fields nullable and add copyWith (#284). (57eceb9b)
  • REFACTOR: Migrate tokenizer to langchain_tiktoken package (#285). (6a3b6466)
  • FEAT: Update internal dependencies (#291). (69621cc6)

langchain_mistralai - v0.0.2

  • REFACTOR: Use cl100k_base encoding model when no tokenizer is available (#295). (ca908e80)
  • REFACTOR: Make all LLM options fields nullable and add copyWith (#284). (57eceb9b)
  • REFACTOR: Migrate tokenizer to langchain_tiktoken package (#285). (6a3b6466)
  • FEAT: Update internal dependencies (#291). (69621cc6)

langchain_ollama - v0.0.3

  • REFACTOR: Use cl100k_base encoding model when no tokenizer is available (#295). (ca908e80)
  • REFACTOR: Make all LLM options fields nullable and add copyWith (#284). (57eceb9b)
  • REFACTOR: Migrate tokenizer to langchain_tiktoken package (#285). (6a3b6466)
  • FEAT: Update internal dependencies (#291). (69621cc6)

openai_dart - v0.1.4

googleai_dart - v0.0.2+1

  • REFACTOR: Make all LLM options fields nullable and add copyWith (#284). (57eceb9b)

mistralai_dart - v0.0.2+1

  • REFACTOR: Make all LLM options fields nullable and add copyWith (#284). (57eceb9b)

vertex_ai - v0.0.8

2024-01-04

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_ollama - v0.0.2+1
  • langchain_mistralai - v0.0.1+4
  • langchain_google - v0.2.2+1
  • langchain_pinecone - v0.0.6+10
  • langchain_chroma - v0.1.0+11
  • langchain_openai - v0.3.1+1

langchain - v0.3.1+1

  • FIX: Export token_buffer.dart (ConversationTokenBufferMemory) (#280). (265fcb4b)

2023-12-26

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_chroma - v0.1.0+10
  • langchain_pinecone - v0.0.6+9
  • langchain_mistralai - v0.0.1+3

langchain - v0.3.1

  • FEAT: Make ChatPromptTemplates more convenient to use (#275). (9f8e6f75)

langchain_ollama - v0.0.2

  • FEAT: Migrate ChatOllama to Ollama chat API and add multi-modal support (#279). (c5de7e12)

ollama_dart - v0.0.2

  • FEAT: Add support for chat API and multi-modal LLMs (#274). (76e1a294)

openai_dart - v0.1.3

langchain_google - v0.2.2

  • Update a dependency to the latest release.

langchain_openai - v0.3.1

  • Update a dependency to the latest release.

mistralai_dart - v0.0.2

  • Update a dependency to the latest release.

chromadb - v0.1.1

  • Update a dependency to the latest release.

googleai_dart - v0.0.2

  • Update a dependency to the latest release.

2023-12-15

Changes

New packages:

Packages with breaking changes:

Packages with other changes:

langchain - v0.3.0

  • BREAKING REFACTOR: Make MIME Type mandatory for base64 images in prompt (#269). (2fe076bb)
  • FEAT: Allow to pass options to countTokens method (#268). (4ecb123b)
  • DOCS: Update README.md and docs (#272). (306a1fdd)

Migration guide

langchain_openai - v0.3.0

  • BREAKING REFACTOR: Make MIME Type mandatory for base64 images in prompt (#269). (2fe076bb)
  • FEAT: Allow to pass options to countTokens method (#268). (4ecb123b)

googleai_dart - v0.0.1

  • FEAT: Implement Dart client for Google AI API (#267). (99083cd2)

langchain_chroma - v0.1.0+9

langchain_google - v0.2.1

  • FEAT: Add support for ChatGoogleGenerativeAI wrapper (Gemini API) (#270). (5d006c12)

langchain_ollama - v0.0.1+2

  • Update a dependency to the latest release.

langchain_mistralai - v0.0.1+1

  • Update a dependency to the latest release.

langchain_pinecone - v0.0.6+8

  • Update a dependency to the latest release.

2023-12-12

Changes

New packages:

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

langchain - v0.2.1

  • FEAT: Support customizing Tool input description (#258). (a9a1b2a0)
  • DOCS: Update Mistral AI documentation (#265). (59b4127e)

langchain_mistralai - v0.0.1

langchain_ollama - v0.0.1+1

  • REFACTOR: Minor changes in ChatOllama. (725b8ff0)

langchain_openai - v0.2.0+1

  • FIX: Fix ChatOpenAI not considering functions from default options (#257). (cd864783)

mistralai_dart - v0.0.1

  • FIX: Wrong role used as system role (#263). (7d68a871)
  • FEAT: Implement Dart client for Mistral AI API (#261). (f4954c59)

openai_dart - v0.1.2+1

  • FIX: Make ChatCompletionNamedToolChoice fields required (#259). (4c7d0436)

langchain_pinecone - v0.0.6+7

  • Update a dependency to the latest release.

langchain_chroma - v0.1.0+8

  • Update a dependency to the latest release.

langchain_google - v0.2.0+1

  • Update a dependency to the latest release.

2023-12-05

Changes

New packages:

Packages with breaking changes:

Packages with other changes:

langchain - v0.2.0

Migration guides:

  • BREAKING FEAT: Move all retriever config options to RetrieverOptions (#248). (f5785b77)
  • BREAKING FEAT: Allow to pass call options to tools (#243). (4a01adb9)
  • FEAT: Allow to mutate default options (#256). (cb5e4058)
  • REFACTOR: Use JsonPath.readValues in JsonLoader (#245). (3e159254)
  • FIX: Out of rage error in ConversationBufferWindowMemory (#249). (1b38bff7)
  • FIX: PromptTemplate stream should only emit if it has all inputs (#247). (a56a2ec5)

langchain_google - v0.2.0

Migration guides:

  • BREAKING FEAT: Move all model config options to VertexAIOptions (#241). (a714882a)
  • BREAKING FEAT: Move all model config options to ChatVertexAIOptions (#242). (89bef8a2)
  • FEAT: Allow to mutate default options (#256). (cb5e4058)

langchain_openai - v0.2.0

Migration guides:

  • BREAKING FEAT: Move all model config options to OpenAIOptions (#232). (16e3e8e4)
  • BREAKING FEAT: Move all model config options to ChatOpenAIOptions (#240). (dd6a21a7)
  • BREAKING FEAT: Allow to pass call options to tools (#243). (4a01adb9)
  • BREAKING FEAT: Move all DallE config options to OpenAIDallEToolOptions (#244). (c24877c6)
  • FEAT: Allow to mutate default options (#256). (cb5e4058)
  • FEAT: Allow to update OpenAI key without having to recreate the wrapper (#246). (05739bd1)
  • FIX: PromptTemplate stream should only emit if it has all inputs (#247). (a56a2ec5)

langchain_chroma - v0.1.0+7

  • DOCS: Fix typo in Chroma docs. (dd97db40)

langchain_ollama - v0.0.1

ollama_dart - v0.0.1+1

openai_dart - v0.1.2

  • FEAT: Allow to update OpenAI key without having to recreate the wrapper (#246). (05739bd1)

langchain_pinecone - v0.0.6+6

  • Update a dependency to the latest release.

2023-11-21

Changes

New packages:

Packages with breaking changes:

  • There are no breaking changes in this release.

ollama_dart - v0.0.1

  • FEAT: Implement ollama_dart, a Dart client for Ollama API (#238). (d213aa9c)

2023-11-20

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_openai - v0.1.2+2
  • langchain_chroma - v0.1.0+6
  • langchain_google - v0.1.0+4

langchain - v0.1.1+1

  • FIX: Conditionally import dart:io in LocalFileStore (#237). (71d337e6)

langchain_pinecone - v0.0.6+5

  • FIX: Decode JSON responses as UTF-8 in Pinecone (#236). (edb427b1)

2023-11-20

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_chroma - v0.1.0+5

chromadb - v0.1.0+2

2023-11-20

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_openai - v0.1.2+1

openai_dart - v0.1.1+2

2023-11-19

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_pinecone - v0.0.6+4
  • langchain_chroma - v0.1.0+4
  • langchain_google - v0.1.0+3

langchain - v0.1.1

  • FEAT: Add support for OpenAIDallETool (#231). (541e8d77)
  • FEAT: Support implementing custom agents using LCEL (#230). (625eeeb4)
  • FEAT: Add support for Runnable.mapInput() (#229). (7cc832ca)
  • REFACTOR: Rename RunnableMapFromItem to RunnableMapFromInput (#228). (7330cfcd)
  • REFACTOR: Improve handling of input and output keys in chains (#227). (acf76b24)

langchain_openai - v0.1.2

  • FEAT: Add support for OpenAIDallETool (#231). (541e8d77)
  • FEAT: Support implementing custom agents using LCEL (#230). (625eeeb4)

2023-11-17

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_openai - v0.1.1+1

openai_dart - v0.1.1+1

  • FIX: Fetch requests with big payloads dropping connection (#226). (1e771098)

2023-11-17

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_pinecone - v0.0.6+3
  • langchain_chroma - v0.1.0+3
  • langchain_google - v0.1.0+2

langchain - v0.1.0+2

langchain_openai - v0.1.1

openai_dart - v0.1.1

2023-11-16

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_chroma - v0.1.0+2

chromadb - v0.1.0+1

  • DOCS: Add public_member_api_docs lint rule and document missing APIs (#223). (52380433)

langchain - v0.1.0+1

  • DOCS: Add public_member_api_docs lint rule and document missing APIs (#223). (52380433)

langchain_google - v0.1.0+1

  • DOCS: Add public_member_api_docs lint rule and document missing APIs (#223). (52380433)

langchain_openai - v0.1.0+1

  • DOCS: Add public_member_api_docs lint rule and document missing APIs (#223). (52380433)

langchain_pinecone - v0.0.6+2

  • DOCS: Add public_member_api_docs lint rule and document missing APIs (#223). (52380433)

openai_dart - v0.1.0+1

  • FIX: Add missing name param in ChatCompletionMessage (#222). (6f186775)
  • FIX: Remove dependency on io.HttpException (#221). (95369e4c)
  • DOCS: Add public_member_api_docs lint rule and document missing APIs (#223). (52380433)

vertex_ai - v0.0.7+2

  • DOCS: Add public_member_api_docs lint rule and document missing APIs (#223). (52380433)

2023-11-15

Changes

Packages with breaking changes:

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_pinecone - v0.0.6+1
  • langchain_chroma - v0.1.0+1

langchain - v0.1.0

  • BREAKING FEAT: Add multi-modal messages support with OpenAI Vision (#220). (6da2e069)

Migration guide

langchain_google - v0.1.0

  • BREAKING FEAT: Add multi-modal messages support with OpenAI Vision (#220). (6da2e069)

Migration guide

langchain_openai - v0.1.0

  • REFACTOR: Align openai_dart client breaking changes (#219). (172db27f)
  • BREAKING FEAT: Add multi-modal messages support with OpenAI Vision (#220). (6da2e069)

Migration guide

openai_dart - v0.1.0

  • BREAKING FEAT: Add multi-modal support (#218). (14c8e7ef)
  • BREAKING FEAT: Rename factory const to more meaningful names (#215). (7e4602fa)
  • FEAT: Add gpt-3.5-turbo-1106 chat model (#217). (73f37915)
  • REFACTOR: Improve request error handling (#214). (4a9f3d33)

Migration guides: new factories and multi-modal

2023-11-13

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

langchain_pinecone - v0.0.6

  • FEAT: Add support for global headers in Pinecone (#213). (8e0d221f)

2023-11-12

Changes

Packages with breaking changes:

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_openai - v0.0.15+2

langchain_chroma - v0.1.0

  • BREAKING FEAT: Chroma databases, tenants and global headers support (#211). (5a1d8397)

chromadb - v0.1.0

  • BREAKING FEAT: Multi-modal and tenants support (#210). (bfb0d89c)

openai_dart - v0.0.2+2

  • REFACTOR: Migrate to generated client stream methods (#208). (9122f551)
  • FIX: Fix integer overflow when targeting web (#207). (eaf69f32)

2023-11-09

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

langchain_chroma - v0.0.5+3

  • DOCS: Update vector stores documentation. (dad60d24)

langchain_google - v0.0.10+1

  • DOCS: Update vector stores documentation. (dad60d24)

langchain_openai - v0.0.15+1

  • REFACTOR: Rename ChatCompletionFunction to FunctionObject (internal) (#206). (0f06df3f)

langchain_pinecone - v0.0.5+2

  • DOCS: Update vector stores documentation. (dad60d24)

openai_dart - v0.0.2+1

  • REFACTOR: Rename ChatCompletionFunction to FunctionObject (#206). (0f06df3f)

2023-11-07

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_pinecone - v0.0.5+1
  • langchain_chroma - v0.0.5+2

langchain - v0.0.15

  • FEAT: Add streaming support in LangChain Expression Language (#192). (2e4bcf91)
  • DOCS: Add streaming to docs. (bb87c190)
  • FEAT: Add streaming support to OutputFunctionsParsers (#194). (8b4e6a13)
  • FIX: Remove unused generic param in StringOutputParser (#193). (decd3176)

langchain_openai - v0.0.15

  • FEAT: Add streaming support to OpenAI (#196). (b21fcb38)
  • FEAT: Support seed and system_fingerprint in OpenAI wrapper (#204). (c31b6795)
  • FEAT: Add streaming support to ChatOpenAI (#197). (2268da78)
  • FEAT: Support seed, system_fingerprint and JSON Mode in ChatOpenAI (#205). (3332c228)

langchain_google - v0.0.10

  • FEAT: Add result id in ChatVertexAI generations (#195). (a5bea6d3)

openai_dart - v0.0.2

  • FEAT: Support new models API functionality (#203). (33ebe746)
  • FEAT: Support new images API functionality (#202). (fcf21daf)
  • FEAT: Support new fine-tunning API functionality (#201). (f5f44ad8)
  • FEAT: Support new embeddings API functionality (#200). (9b43d85b)
  • FEAT: Support new completion API functionality (#199). (f12f6f57)
  • FEAT: Support new chat completion API functionality (#198). (01820d69)
  • FIX: Handle nullable function call fields when streaming (#191). (8f23cf16)

2023-11-03

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

langchain_chroma - v0.0.5+1

langchain_openai - v0.0.14+1

  • FIX: Revert OpenAI maxTokens default to 256 (#189). (ab2ce6d4)
  • DOCS: Update CHANGELOG.md. (5ea4e532)

langchain_pinecone - v0.0.5

2023-11-02

Changes

New packages:

Packages with breaking changes:

Packages with other changes:

langchain - v0.0.14

  • BREAKING FIX: Change loaders lastModified metadata field to integer (#172). (72c724f8)
  • BREAKING FEAT: Update uuid internal dependency to 4.x.x (#173). (b01f4afe)
  • REFACTOR: Don't require implement getFormatInstructions. (d8b1286d)
  • DOCS: Update docs. (af7ee827)

langchain_openai - v0.0.14

  • FEAT: Migrate OpenAI to openai_dart client (#184). (6c90b371)
  • FEAT: Migrate ChatOpenAI to openai_dart client (#185). (de8f487d)
  • FEAT: Migrate OpenAIEmbeddings to openai_dart client (#183). (8f626fe8)
  • REFACTOR: Remove dependency on dart_openai (#186). (273cfa2e)

langchain_chroma - v0.0.5

  • BREAKING FIX: Change loaders lastModified metadata field to integer (#172). (72c724f8)
  • BREAKING FEAT: Update uuid internal dependency to 4.x.x (#173). (b01f4afe)
  • DOCS: Update changelog. (d45d624a)

langchain_google - v0.0.9

  • BREAKING FEAT: Update uuid internal dependency to 4.x.x (#173). (b01f4afe)
  • DOCS: Update changelog. (d45d624a)

langchain_pinecone - v0.0.4

  • BREAKING FEAT: Update uuid internal dependency to 4.x.x (#173). (b01f4afe)

openai_dart - v0.0.1

  • FIX: Fix static analysis warning (#187). (3fe91570)
  • FIX: Several fixes and improvments (#182). (115e8bef)
  • FEAT: Support different embedding response formats (#180). (4f676e87)
  • FEAT: Implement openai_dart, a Dart client for OpenAI API (#178). (fa5d032a)

2023-09-17

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

langchain - v0.0.13

langchain_openai - v0.0.13

  • FEAT: Implement LangChain Expression Language (LCEL) (#163). (85ea41af)

langchain_pinecone - v0.0.3

langchain_chroma - v0.0.4

  • Updated langchain dependency

langchain_google - v0.0.8

  • Updated langchain dependency

2023-09-08

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

langchain_google - v0.0.7+1

  • REFACTOR: Require http.Client instead of AuthClient (#156). (0f7fee7f)

langchain_pinecone - v0.0.2+1

  • REFACTOR: Require http.Client instead of AuthClient (#156). (0f7fee7f)

vertex_ai - v0.0.7+1

  • REFACTOR: Require http.Client instead of AuthClient (#156). (0f7fee7f)

2023-09-05

Changes

Packages with breaking changes:

Packages with other changes:

langchain - v0.0.12

  • BREAKING REFACTOR: Change embedDocuments input to List<Document> (#153). (1b5d6fbf)
  • DOCS: Acknowledge sponsors in readme. (092d94c8)
  • DOCS: Add topics to pubspecs. (8c1d6297)

langchain_google - v0.0.7

  • BREAKING FEAT: Add default and call options in VertexAI and ChatVertexAI (#155). (fe1b12ea)
  • BREAKING REFACTOR: Change embedDocuments input to List<Document> (#153). (1b5d6fbf)
  • FEAT: Support document title in VertexAIEmbeddings (#154). (6b763731)
  • FEAT: Support task type in VertexAIEmbeddings (#151). (8a2199e2)
  • DOCS: Add topics to pubspecs. (8c1d6297)

langchain_openai - v0.0.12

  • BREAKING REFACTOR: Change embedDocuments input to List<Document> (#153). (1b5d6fbf)
  • DOCS: Add topics to pubspecs. (8c1d6297)

langchain_pinecone - v0.0.2

langchain_chroma - v0.0.3

  • DOCS: Add topics to pubspecs. (8c1d6297)

vertex_ai - v0.0.7

  • FEAT: Add support for stopSequence and candidateCount (#150). (eab7d968)
  • FEAT: Support task type and title in embeddings models (#149). (421d36bd)
  • FIX: Fix typo in stop sequences field deserialization (#152). (4f7161da)
  • DOCS: Add topics to pubspecs. (8c1d6297)

chromadb - v0.0.3

  • DOCS: Add topics to pubspecs. (8c1d6297)

2023-08-31

Changes

New packages:

Packages with breaking changes:

Packages with other changes:

langchain - v0.0.11

  • DOCS: Update readme. (e1b5b295)
  • BREAKING REFACTOR: Remove addDocuments from VectorStoreRetriever (#146). (d32a5fd9)
  • BREAKING REFACTOR: Rename VectorStoreRetrieverMemory and require vector store (#145). (67af3195)

langchain_pinecone - v0.0.1

  • DOCS: Update readme. (e1b5b295)
  • DOCS: Update packages example. (4f8488fc)
  • FEAT: Add support for Pinecone VectorStore (#37). (e43eef97)

langchain_google - v0.0.6

  • DOCS: Update packages example. (4f8488fc)

langchain_openai - v0.0.11

  • FEAT: Add ability to specify user in OpenAI and ChatOpenAI (#143). (457ab54e)
  • DOCS: Update packages example. (4f8488fc)

langchain_chroma - v0.0.2

vertex_ai - v0.0.6

  • FIX: typecast exception when null publicationDate (#148). (d4afc131)
  • DOCS: Update packages example. (4f8488fc)

chromadb - v0.0.2

  • REFACTOR: Update generated Chroma API client (#142). (4f0e7379)

2023-08-27

Changes

Packages with changes:

New packages:

langchain - v0.0.10

langchain_google - v0.0.5

langchain_openai - v0.0.10

langchain_chroma - v0.0.1

  • FEAT: Add support for Chroma VectorStore (#139). (098783b4)

vertex_ai - v0.0.5

chromadb - v0.0.1

  • FEAT: Add Chroma embedding database API client (#140). (5fdcbc52)

2023-08-23

Changes

Packages with breaking changes:

  • There are no breaking changes in this release.

Packages with other changes:

langchain - v0.0.9

  • FEAT: Support filtering in MemoryVectorStore (#137). (84da480f)
  • FEAT: Support filtering in VertexAI Matching Engine (#136). (768c6987)
  • FEAT: Allow to pass vector search config (#135). (5b8fa5a3)
  • DOCS: Fix API documentation errors (#138). (1aa38fce)

langchain_google - v0.0.4

  • FEAT: Support filtering in VertexAI Matching Engine (#136). (768c6987)
  • FEAT: Allow to pass vector search config (#135). (5b8fa5a3)
  • DOCS: Fix API documentation errors (#138). (1aa38fce)

langchain_openai - v0.0.9

vertex_ai - v0.0.4

2023-08-20

Changes

Packages with changes:

langchain_openai - v0.0.8+1

  • FIX: OpenAIFunctionsAgent wrong prompt order with no memory (#134). (8c9dcf22)

2023-08-19

Changes

Packages with changes:

langchain - v0.0.8

  • REFACTOR: Rename store folder to chat_message_history (#126). (fa54c7e2)
  • REFACTOR: Fix Dart 3.1.0 linter issues (#125). (cc32f3f1)
  • FEAT: Add support for LocalFileStore (#132). (2c508dce)
  • FEAT: Add support for CacheBackedEmbeddings (#131). (27d8b777)
  • FEAT: Add FakeEmbeddings testing model (#130). (f06920d7)
  • FEAT: Add support for EncoderBackedStore (#129). (85bb3191)
  • FEAT: Add support for InMemoryStore (#128). (699c0904)
  • FEAT: Add support for InMemoryDocStore (#127). (d9d7268d)
  • FEAT: Initial vectors, ids, and delete in MemoryVectorStore (#123). (f87a738d)

langchain_google - v0.0.3

  • FEAT: Infeer queryRootUrl in VertexAIMatchingEngine (#133). (c5353368)

langchain_openai - v0.0.8

vertex_ai - v0.0.3

2023-08-16

Changes

Packages with changes:

Packages with dependency updates only:

Packages listed below depend on other packages in this workspace that have had changes. Their versions have been incremented to bump the minimum dependency versions of the packages they depend upon in this project.

  • langchain_openai - v0.0.7+1
  • langchain_google - v0.0.2+2

langchain - v0.0.7+1

  • FIX: Text splitters were not preserving docs IDs (#122). (a9d7f098)

2023-08-16

Changes

Packages with changes:

langchain_google - v0.0.2+1

  • DOCS: Add VertexAI Matching Engine sample setup script (#121). (ed2e1549)

vertex_ai - v0.0.2+1

  • FIX: approximateNeighborsCount deserialization issue (#120). (f3381208)
  • DOCS: Update readme. (81f67c5e)

2023-08-16

Changes

Packages with changes:

langchain - v0.0.7

  • FEAT: Integrate Vertex AI Matching Engine vector store (#103). (289c3eef)

langchain_google - v0.0.2

  • FEAT: Integrate Vertex AI Matching Engine vector store (#103). (289c3eef)

langchain_openai - v0.0.7

  • Updated langchain dependency

vertex_ai - v0.0.2

  • FEAT: Add GCP Vertex AI Matching Engine client (#116). (2c1bbfcc)

2023-08-13

Changes

Packages with changes:

New packages:

langchain - v0.0.6

  • REFACTOR: Always await or explicitly discard Futures (#106). (989e93db)
  • FIX: Fix OpenAIQAWithSourcesChain returning empty strings (#113). (6181ff8d)
  • FIX: VectorStore k variable was ignored (#110). (80e61eb7)

langchain_openai - v0.0.6

  • REFACTOR: Always await or explicitly discard Futures (#106). (989e93db)
  • FIX: Fix OpenAIQAWithSourcesChain returning empty strings (#113). (6181ff8d)

langchain_google - v0.0.1

  • FEAT: Integrate Google Vertex AI PaLM Text model (#98). (b2746c23)
  • FEAT: Integrate Google Vertex AI PaLM Chat Model (#99). (3897595d)
  • FEAT: Integrate Google Vertex AI PaLM Embeddings (#100). (d777eccc)

vertex_ai - v0.0.1

  • REFACTOR: Move Vertex AI client to its own package (#111). (d8aea156)

2023-08-09

Changes

Packages with changes:

langchain - v0.0.5+1

  • FIX: OpenAIOptions class not exported (#104). (e50efc3d)
  • DOCS: Improve RetrievalQAChain API documentation (#95). (e6d0a9d3)

langchain_openai - v0.0.5+1

2023-08-06

Changes

Packages with changes:

langchain - v0.0.5

  • FIX: Suff and MapReduce docs chains don't handle chat messages (#92). (19182ca1)
  • FEAT: Update AgentExecutor constructor to use agent's tools (#89). (3af56a45)
  • FEAT: Add MessagePlaceholder (#87). (23ee95b6)
  • DOCS: Update CONTRIBUTING.md. (5f2b9264)
  • DOCS: Fix typo in MessagePlaceholder API docs (#90). (f53e1a2b)

langchain_openai - v0.0.5

  • FIX: FunctionChatMessage not saved properly in memory (#88). (d7b763de)
  • FEAT: Update AgentExecutor constructor to use agent's tools (#89). (3af56a45)
  • DOCS: Add example of using memory in OpenAIFunctionsAgent (#91). (898d5350)

2023-08-05

Changes

Packages with changes:

langchain - v0.0.4

  • REFACTOR: Extract default memory key and prefixes to constants. (750fd01a)
  • FIX: systemChatMessage was ignored in OpenAIFunctionsAgent (#86). (cfe1e009)
  • FIX: Allow to add memory to an agent executor (#80). (8110464c)
  • FEAT: Add ConversationSummaryMemory (#27). (f631d9e5)
  • FEAT: Support LLMChain in OpenAIFunctionsAgent and memory. (bd4a1cb9)
  • FEAT: Return ChatMessage when LLMChain used with ChatModel. (bb5f4d23)
  • FEAT: Add FakeChatModel for testing purposes. (659783a6)
  • FEAT: Add support for ConversationTokenBufferMemory (#26). (8113d1c0)
  • FEAT: Improve SummarizeChain.mapReduce summaryMaxTokens name and docs. (0be06e02)
  • FEAT: Add support for CsvLoader (#77). (41d24e76)
  • FEAT: Add ConversationBufferWindowMemory (#25). (9c271f7e)

langchain_openai - v0.0.4

  • FIX: systemChatMessage was ignored in OpenAIFunctionsAgent (#86). (cfe1e009)
  • FEAT: Support LLMChain in OpenAIFunctionsAgent and memory. (bd4a1cb9)
  • FEAT: Return ChatMessage when LLMChain used with ChatModel. (bb5f4d23)

2023-07-28

Changes

Packages with changes:

langchain - v0.0.3

  • FIX: Loaders tests. (f0498300)
  • FEAT: Update internal dependencies (including http to 1.1.0). (8f3e8bc8)
  • FEAT: Add support for VectorStoreRetrieverMemory (#54). (72cd1b10)

langchain_openai - v0.0.3

  • FEAT: Update internal dependencies (including http to 1.1.0). (8f3e8bc8)

2023-07-23

Changes

Packages with changes:

langchain - v0.0.2

  • FIX: OpenAIQAWithSourcesChain throws exception. (45c6cb9d)
  • FEAT: Add support for SummarizeChain (#58). (9499fc04)
  • FEAT: Add support for SequentialChain class (#30). (381a6768)
  • FEAT: Add support for WebBaseLoader (#74). (0b5bf4b0)
  • FEAT: Add Support for JsonLoader (#72). (2457a973)
  • FEAT: Add support for MapReduceDocumentsChain (#59). (9f2190c4)
  • FEAT: Add support for ReduceDocumentsChain (#70). (34cf10bd)
  • FEAT: Support estimating the number of tokens for a given prompt (#3). (e22f22c8)
  • FEAT: Add support for CodeTextSplitter (#63). (92a8c7da)
  • FEAT: Add support for RecursiveCharacterTextSplitter (#61). (697cdcbf)
  • DOCS: Document sequential chain. (b9693a4e)
  • DOCS: Document text, json and web loaders. (a95b3e9f)
  • DOCS: Update API docs. (7bfa6d17)
  • DOCS: Update readme. (dd394715)

langchain_openai - v0.0.2

  • FIX: OpenAIQAWithSourcesChain throws exception. (45c6cb9d)
  • FEAT: Support estimating the number of tokens for a given prompt (#3). (e22f22c8)