langchain_ollama 0.2.2 copy "langchain_ollama: ^0.2.2" to clipboard
langchain_ollama: ^0.2.2 copied to clipboard

Published 8 days ago • verified publisherdavidmiguel.comDart 3 compatible
SDKDartFlutter
PlatformAndroidiOSLinuxmacOSwebWindows
→

Metadata

LangChain.dart integration module for Ollama (run Llama 3, Phi-3, WizardLM-2, Mistral 7B, Gemma and other models locally).

More...

0.2.2 #

  • FEAT: Add Runnable.close() to close any resources associated with it (#439). (4e08cced)

0.2.1+1 #

  • Update a dependency to the latest release.

0.2.1 #

  • 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)

0.2.0 #

Note: This release has breaking changes.
If you are using "function calling" check how to migrate to "tool calling".

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

0.1.0+2 #

  • Update a dependency to the latest release.

0.1.0+1 #

  • Update a dependency to the latest release.

0.1.0 #

Note: This release has breaking changes.
Migration guide

  • 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)

0.0.4 #

  • 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)

0.0.3+3 #

0.0.3+2 #

  • Update a dependency to the latest release.

0.0.3+1 #

  • Update a dependency to the latest release.

0.0.3 #

  • 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)

0.0.2+1 #

  • Update a dependency to the latest release.

0.0.2 #

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

0.0.1+3 #

  • Update a dependency to the latest release.

0.0.1+2 #

  • Update a dependency to the latest release.

0.0.1+1 #

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

0.0.1 #

0.0.1-dev.1 #

  • Bootstrap project.

← Metadata

3
likes
150
pub points
87%
popularity

Publisher

verified publisherdavidmiguel.com

Metadata

LangChain.dart integration module for Ollama (run Llama 3, Phi-3, WizardLM-2, Mistral 7B, Gemma and other models locally).

Homepage
Repository (GitHub)
View/report issues
Contributing

Topics

#ai #nlp #llms #langchain #ollama

Documentation

Documentation
API reference

License

MIT (LICENSE)

Dependencies

collection, http, langchain_core, langchain_tiktoken, meta, ollama_dart, uuid

More

Packages that depend on langchain_ollama

Back