fix: streaming for Agent.createTask

[himself65]

Fixes: #590

Feedback from users, who want to show a response for each task output, because it will have a long time polling for function call

Roadmap

• Readable Stream implementation
• Eary return stream response, then we handle function call (llm.call -> user time -> handle llm.call -> next round)
• Give some ability to user to modify current run? (not sure if this is good)

Update

• should we implement our queuingStrategy with log(function call + time) cost???

[changeset-bot]

🦋 Changeset detected

Latest commit: 9b7c650

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 7 packages

Name	Type
llamaindex	Patch
@llamaindex/core-e2e	Patch
docs	Patch
@llamaindex/experimental	Patch
@llamaindex/cloudflare-worker-agent-test	Patch
@llamaindex/next-agent-test	Patch
@llamaindex/waku-query-engine-test	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
llama-index-ts-docs	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 2, 2024 0:29am