Skip to content

Commit dbf98b7

Browse files
committed
fix: stabilize concurrent PDF parsing
1 parent 88e02e6 commit dbf98b7

37 files changed

Lines changed: 320 additions & 189 deletions

deploy/version/v4.15/docker-compose.template.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -133,7 +133,7 @@ x-service-env-config: &x-service-env-config
133133
CHAT_TITLE_MODEL:
134134
SKIP_FILE_TYPE_CHECK: false
135135
WECHAT_CHANNEL_CONCURRENCY: 1000
136-
PARSE_FILE_WORKERS: 10
136+
PARSE_FILE_WORKERS: 5
137137
PARSE_FILE_TIMEOUT_SECONDS: 600
138138
HTML_TO_MARKDOWN_WORKERS: 10
139139
TEXT_TO_CHUNKS_WORKERS: 10

document/content/self-host/config/env.en.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -182,7 +182,7 @@ These variables are mainly validated by `packages/service/env.ts` and apply to `
182182
| `AGENT_ENGINE` | `fastAgent` | Agent engine. Supported values are `fastAgent` and `piAgent`. |
183183
| `SKIP_FILE_TYPE_CHECK` | `false` | Whether upload file type checks are skipped. |
184184
| `WECHAT_CHANNEL_CONCURRENCY` | `1000` | WeChat channel poll worker concurrency. Minimum value is `10`. |
185-
| `PARSE_FILE_WORKERS` | `10` | Resident file parsing worker count. |
185+
| `PARSE_FILE_WORKERS` | `5` | Resident file parsing worker count. |
186186
| `HTML_TO_MARKDOWN_WORKERS` | `10` | Resident HTML-to-Markdown worker count. |
187187
| `TEXT_TO_CHUNKS_WORKERS` | `10` | Resident text chunking worker count. |
188188
| `PARSE_FILE_TIMEOUT_SECONDS` | `600` | Timeout for one file parsing task, in seconds. |

document/content/self-host/config/env.mdx

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -182,7 +182,7 @@ description: projects/app、projects/code-sandbox 与 pro/admin 环境变量说
182182
| `AGENT_ENGINE` | `fastAgent` | Agent 引擎,可选 `fastAgent``piAgent`|
183183
| `SKIP_FILE_TYPE_CHECK` | `false` | 是否跳过上传文件类型检查。 |
184184
| `WECHAT_CHANNEL_CONCURRENCY` | `1000` | 微信渠道 poll worker 并发数,最小 `10`|
185-
| `PARSE_FILE_WORKERS` | `10` | 文件解析 worker 常驻线程数。 |
185+
| `PARSE_FILE_WORKERS` | `5` | 文件解析 worker 常驻线程数。 |
186186
| `HTML_TO_MARKDOWN_WORKERS` | `10` | HTML 转 Markdown worker 常驻线程数。 |
187187
| `TEXT_TO_CHUNKS_WORKERS` | `10` | 文本切块 worker 常驻线程数。 |
188188
| `PARSE_FILE_TIMEOUT_SECONDS` | `600` | 文件解析单任务超时时间,单位秒。 |

document/content/self-host/upgrading/4-15/4152.en.mdx

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -42,7 +42,8 @@ The previous values are no longer supported. Using `default` or `pi` will fail e
4242
5. Files generated by system tools no longer expire after 1 hour. They are now long-lived and deleted together with the conversation.
4343
6. The registration button is now hidden in Sync Mode.
4444
7. Improved the performance of the fade-in effect for streaming output in chat dialogs.
45-
8. Upgraded `LiteParse` to fix PDF parsing errors under concurrent workloads.
45+
8. Upgraded `LiteParse` to fix PDF parsing errors under concurrent workloads. The default file parsing worker count is now 5 instead of 10 and remains configurable through `PARSE_FILE_WORKERS`.
46+
9. Added in-flight request deduplication for the model list and sandbox package endpoints. Identical concurrent requests now share the same result, reducing duplicate requests triggered by workflow nodes and selectors.
4647

4748
### Streaming Markdown Rendering Improvements
4849

document/content/self-host/upgrading/4-15/4152.mdx

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -40,7 +40,8 @@ V4.15.2 起,`AGENT_ENGINE` 使用新的枚举值。升级前,请按下表修
4040
5. 系统工具生成的文件不会 1 小时过期,改成长期,跟随会话一起删除。
4141
6. 同步模式下不显示注册用户按钮。
4242
7. 对话框流输出,淡入效果性能优化。
43-
8. 升级 `LiteParse` 版本,解决并发解析 PDF 报错问题。
43+
8. 升级 `LiteParse` 版本,解决并发解析 PDF 报错问题;文件解析 worker 默认数量由 10 调整为 5,仍可通过 `PARSE_FILE_WORKERS` 配置。
44+
9. 前端请求增加并发去重能力,模型列表和沙盒依赖接口的相同请求会复用进行中的结果,减少工作流节点和选择器重复触发的请求。
4445

4546
## 🐛 修复
4647

document/data/doc-last-modified.json

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -320,8 +320,8 @@
320320
"content/self-host/upgrading/4-15/41507.mdx": "2026-06-30T17:31:43+08:00",
321321
"content/self-host/upgrading/4-15/4151.en.mdx": "2026-07-07T21:14:28+08:00",
322322
"content/self-host/upgrading/4-15/4151.mdx": "2026-07-07T21:14:28+08:00",
323-
"content/self-host/upgrading/4-15/4152.en.mdx": "2026-07-16T13:18:15+08:00",
324-
"content/self-host/upgrading/4-15/4152.mdx": "2026-07-16T17:25:54+08:00",
323+
"content/self-host/upgrading/4-15/4152.en.mdx": "2026-07-16T17:54:31+08:00",
324+
"content/self-host/upgrading/4-15/4152.mdx": "2026-07-16T17:54:31+08:00",
325325
"content/self-host/upgrading/outdated/40.en.mdx": "2026-04-26T21:08:47+08:00",
326326
"content/self-host/upgrading/outdated/40.mdx": "2026-04-26T21:08:47+08:00",
327327
"content/self-host/upgrading/outdated/41.en.mdx": "2026-04-26T21:08:47+08:00",

document/public/deploy/docker/v4.15/cn/docker-compose.milvus.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -133,7 +133,7 @@ x-service-env-config: &x-service-env-config
133133
CHAT_TITLE_MODEL:
134134
SKIP_FILE_TYPE_CHECK: false
135135
WECHAT_CHANNEL_CONCURRENCY: 1000
136-
PARSE_FILE_WORKERS: 10
136+
PARSE_FILE_WORKERS: 5
137137
PARSE_FILE_TIMEOUT_SECONDS: 600
138138
HTML_TO_MARKDOWN_WORKERS: 10
139139
TEXT_TO_CHUNKS_WORKERS: 10

document/public/deploy/docker/v4.15/cn/docker-compose.oceanbase.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -133,7 +133,7 @@ x-service-env-config: &x-service-env-config
133133
CHAT_TITLE_MODEL:
134134
SKIP_FILE_TYPE_CHECK: false
135135
WECHAT_CHANNEL_CONCURRENCY: 1000
136-
PARSE_FILE_WORKERS: 10
136+
PARSE_FILE_WORKERS: 5
137137
PARSE_FILE_TIMEOUT_SECONDS: 600
138138
HTML_TO_MARKDOWN_WORKERS: 10
139139
TEXT_TO_CHUNKS_WORKERS: 10

document/public/deploy/docker/v4.15/cn/docker-compose.opengauss.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -133,7 +133,7 @@ x-service-env-config: &x-service-env-config
133133
CHAT_TITLE_MODEL:
134134
SKIP_FILE_TYPE_CHECK: false
135135
WECHAT_CHANNEL_CONCURRENCY: 1000
136-
PARSE_FILE_WORKERS: 10
136+
PARSE_FILE_WORKERS: 5
137137
PARSE_FILE_TIMEOUT_SECONDS: 600
138138
HTML_TO_MARKDOWN_WORKERS: 10
139139
TEXT_TO_CHUNKS_WORKERS: 10

document/public/deploy/docker/v4.15/cn/docker-compose.pg.yml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -133,7 +133,7 @@ x-service-env-config: &x-service-env-config
133133
CHAT_TITLE_MODEL:
134134
SKIP_FILE_TYPE_CHECK: false
135135
WECHAT_CHANNEL_CONCURRENCY: 1000
136-
PARSE_FILE_WORKERS: 10
136+
PARSE_FILE_WORKERS: 5
137137
PARSE_FILE_TIMEOUT_SECONDS: 600
138138
HTML_TO_MARKDOWN_WORKERS: 10
139139
TEXT_TO_CHUNKS_WORKERS: 10

0 commit comments

Comments
 (0)