-
Notifications
You must be signed in to change notification settings - Fork 156
feat: add response_format
param to OllamaChatGenerator
#1282
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Hey! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice...
I found some potential improvements.
...rations/ollama/src/haystack_integrations/components/generators/ollama/chat/chat_generator.py
Show resolved
Hide resolved
…index (#1277) * fix: Add schema name if dropping index in pgvector store * fix: Remove check for deletion in src * new integration test --------- Co-authored-by: anakin87 <[email protected]>
* progress * Ollama: add support for tools * make generator tests run with llama * PR feedback + simplification
* Add Secret handling in OpenSearchDocumentStore * only serialize auth secrets when values are resolvable * Update integrations/opensearch/src/haystack_integrations/document_stores/opensearch/document_store.py Co-authored-by: tstadel <[email protected]> * Fixes * Revert accidental commit * Special list of Secrets handling only, keep everything else as it was before * Small improvement * More simplifications --------- Co-authored-by: tstadel <[email protected]>
* AmazonBedrockChatGenerator - add tools support * Remove test not needed * Add actual pipeline integration test with tools * Extract instance functions to free standing * No need to test serde on all models * Add serde test * Fix serde test * Lint * Always pack thinking + tool call into single ChatMessage * Revert accidental changes * Method renaming for Python Zen * Add class pydocs * Don't run pipeline in serde test * Update test_serde_in_pipeline test * Lint
* AmazonBedrockGenerator - remove truncation * Update tests * Linting * Remove deprecation test * Update docs config * Update integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/generator.py Co-authored-by: Stefano Fiorucci <[email protected]> * Lint --------- Co-authored-by: Stefano Fiorucci <[email protected]>
… and Ranker in the type (#1320) * updating amazon-bedrock readme * alphabetical order
Bumps [fossas/fossa-action](https://github.com/fossas/fossa-action) from 1.4.0 to 1.5.0. - [Release notes](https://github.com/fossas/fossa-action/releases) - [Commits](fossas/fossa-action@v1.4.0...v1.5.0) --- updated-dependencies: - dependency-name: fossas/fossa-action dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Created a replacement PR #1326 for this issue. |
Related Issues
Proposed Changes:
Add a new param
response_format
to the OllamaChatGenerator to support structured outputs.How did you test it?
Updated the tests
Notes for the reviewer
Checklist
fix:
,feat:
,build:
,chore:
,ci:
,docs:
,style:
,refactor:
,perf:
,test:
.