[PR #29131] perf: optimize generate conversation name #32306

Closed
opened 2026-02-21 20:51:09 -05:00 by yindo · 0 comments
Owner

Original Pull Request: https://github.com/langgenius/dify/pull/29131

State: closed
Merged: Yes


Important

  1. Make sure you have read our contribution guidelines
  2. Ensure there is an associated issue and you have been assigned to it
  3. Use the correct syntax to link this PR: Fixes #<issue number>.

Summary

original:

User sends message

Create session and message (Database operations) ~0.26s → 0.09s (Optimized)

Start streaming response generation

Concurrently start conversation title generation thread → LLM call 1-3s

Streamed content gradually output to user

Streaming output completes

Wait for conversation title generation thread to complete join() ← 🚨 Bottleneck: Blocks for 1-3s

Connection closes, user can begin second turn of conversation

new:

User sends message

Create session & message (DB op) ~0.09 s

Start streaming response generation

Stream content to user chunk-by-chunk

Stream finishes

Connection closed immediately ← user can start round-2 at once

[Background] 2 s later, launch dialog-title generation

[Background] LLM call to generate title 1–3 s

[Background] Update dialog title in DB

using daemon second conversation not wait first conversation, add redis cache increase the op

Screenshots

Before After
... ...

Checklist

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods
**Original Pull Request:** https://github.com/langgenius/dify/pull/29131 **State:** closed **Merged:** Yes --- > [!IMPORTANT] > > 1. Make sure you have read our [contribution guidelines](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) > 1. Ensure there is an associated issue and you have been assigned to it > 1. Use the correct syntax to link this PR: `Fixes #<issue number>`. ## Summary original: User sends message ↓ Create session and message (Database operations) ~0.26s → 0.09s (Optimized) ↓ Start streaming response generation ↓ Concurrently start conversation title generation thread → LLM call 1-3s ↓ Streamed content gradually output to user ↓ Streaming output completes ↓ Wait for conversation title generation thread to complete join() ← 🚨 Bottleneck: Blocks for 1-3s ↓ Connection closes, user can begin second turn of conversation new: User sends message ↓ Create session & message (DB op) ~0.09 s ↓ Start streaming response generation ↓ Stream content to user chunk-by-chunk ↓ Stream finishes ↓ Connection closed immediately ← ✅ user can start round-2 at once ↓ [Background] 2 s later, launch dialog-title generation ↓ [Background] LLM call to generate title 1–3 s ↓ [Background] Update dialog title in DB using daemon second conversation not wait first conversation, add redis cache increase the op ## Screenshots | Before | After | |--------|-------| | ... | ... | ## Checklist - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs) - [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!) - [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change. - [x] I've updated the documentation accordingly. - [x] I ran `dev/reformat`(backend) and `cd web && npx lint-staged`(frontend) to appease the lint gods
yindo added the pull-request label 2026-02-21 20:51:09 -05:00
yindo closed this issue 2026-02-21 20:51:09 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#32306