langchain-fireworks
An officially maintained LangChain integration module for Fireworks AI, enabling connection to and invocation of large model inference services provided by Fireworks AI within the LangChain framework. It supports features such as prompt caching and streaming output.
Core Facts
This release record was completed by a GitHub Actions automated workflow and carries an official GitHub verified signature (Verified).
langchain-fireworks is an officially maintained LangChain integration module used to connect to large model inference services provided by Fireworks AI.
Timeline (last 90 days)
The article recommends that projects involving tool calling or Agents prioritize upgrading langchain-fireworks to obtain more developer-friendly error diagnostics
langchain-fireworks 1.6.3 contains three fixes and one data refresh compared to the previous version 1.6.2
Fix #40814 marks Fireworks' native PDF input as unsupported
Fix #40818 causes the new version to retain malformed tool parameter exceptions as diagnostic JSON when a model returns incorrectly formatted tool parameters, rather than silently discarding them or throwing an unreadable error
This update includes a chore(model-profiles) change #40804 that refreshes model profile data
1.7.0 fixes the classification logic for mid-stream read timeouts in streaming output (PR #40874).
1.7.0 refreshes model configuration data (model-profiles, PR #40833) to keep the framework's built-in model metadata in sync with the models currently available on the Fireworks platform.
1.7.0 includes a hotfix (PR #40890) that replaces a model no longer available in integration tests.
LangChain-Fireworks version 1.7.0 adds a prompt caching middleware.
langchain-fireworks is an officially maintained LangChain integration module used to connect to large model inference services provided by Fireworks AI.
3 more timeline events
All Facts (13)
This release record was completed by a GitHub Actions automated workflow and carries an official GitHub verified signature (Verified).
90%Verifiedlangchain-fireworks is an officially maintained LangChain integration module used to connect to large model inference services provided by Fireworks AI.
75%UnverifiedThe article recommends that projects involving tool calling or Agents prioritize upgrading langchain-fireworks to obtain more developer-friendly error diagnostics
50%Unverifiedlangchain-fireworks 1.6.3 contains three fixes and one data refresh compared to the previous version 1.6.2
50%UnverifiedFix #40814 marks Fireworks' native PDF input as unsupported
50%UnverifiedFix #40818 causes the new version to retain malformed tool parameter exceptions as diagnostic JSON when a model returns incorrectly formatted tool parameters, rather than silently discarding them or throwing an unreadable error
50%UnverifiedThis update includes a chore(model-profiles) change #40804 that refreshes model profile data
50%Unverified1.7.0 refreshes model configuration data (model-profiles, PR #40833) to keep the framework's built-in model metadata in sync with the models currently available on the Fireworks platform.
50%UnverifiedThe previous stable version before version 1.7.0 is 1.6.3.
50%UnverifiedThe prompt caching middleware was introduced by PR #38823.
50%Unverified1.7.0 fixes the classification logic for mid-stream read timeouts in streaming output (PR #40874).
50%Unverified1.7.0 includes a hotfix (PR #40890) that replaces a model no longer available in integration tests.
50%UnverifiedLangChain-Fireworks version 1.7.0 adds a prompt caching middleware.
50%