langchain-hs-openai

OpenAI provider and embeddings for langchain-hs

https://github.com/tusharad/langchain-hs#readme

Stackage Nightly 2026-11-14:0.0.6.2
Latest on Hackage:0.0.6.2

See all snapshots langchain-hs-openai appears in

MIT licensed by Tushar Adhatrao
Maintained by [email protected]
This version can be pinned in stack with:langchain-hs-openai-0.0.6.2@sha256:331164d0e13b3997f950d22ff72f26e816574fe8674694484a9e1b86558755a8,3222

Module documentation for 0.0.6.2

langchain-hs-openai

OpenAI ChatModel provider and embeddings for langchain-hs.

Supports OpenAI and any OpenAI-compatible endpoint (OpenRouter, Fireworks, Together AI). Does not depend on Ollama or Gemini packages.

Installation

# stack.yaml extra-deps
- langchain-hs-openai-0.0.6.2

# package.yaml / .cabal
dependencies:
  - langchain-hs-openai

Usage

import Langchain.Provider.OpenAI
import Control.Monad.Except (runExceptT)

main :: IO ()
main = do
  let model = newOpenAI "sk-..." "gpt-4o"
  res <- runExceptT $ invoke model [userMessage "Hello"] Nothing
  print res

Changes

Changelog for langchain-hs-openai

0.0.6.2 - 2026-11-14

Note: 0.0.6.1 was skipped globally after langchain-hs-ollama-v0.0.6.1.

  • Added incremental SSE tool-call delta accumulation and LLMChunk "" (Just toolCall) emission in ChatModel.stream.
  • Coordinated monorepo release alignment to 0.0.6.2 and updated langchain-hs-core dependency bound to >= 0.0.6.2 && < 0.0.7.

0.0.6.0 - 2026-10-02

  • Initial release. Split from the monolithic langchain-hs package.
  • Provides Langchain.Provider.OpenAI and Langchain.Embeddings.OpenAI.