open-webui/Fu-Jie_openwebui-extensions
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix: Remove duplicate parameters and correct documentation

Browse Source
This commit is contained in:
fujie
2026-01-15 00:24:52 +08:00
parent 8868b28a84
commit e4cbf231a6
23 changed files with 856 additions and 218 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
plugins/filters/async-context-compression/README.md
View File

@@ -1,6 +1,6 @@
# Async Context Compression Filter
**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 1.1.3 | **License:** MIT
**Author:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **Version:** 1.1.3 | **License:** MIT
This filter reduces token consumption in long conversations through intelligent summarization and message compression while keeping conversations coherent.

2
plugins/filters/async-context-compression/README_CN.md
View File

@@ -1,6 +1,6 @@
# 异步上下文压缩过滤器
**作者:** [Fu-Jie](https://github.com/Fu-Jie) | **版本:** 1.1.3 | **许可证:** MIT
**作者:** [Fu-Jie](https://github.com/Fu-Jie/awesome-openwebui) | **版本:** 1.1.3 | **许可证:** MIT
> **重要提示**：为了确保所有过滤器的可维护性和易用性，每个过滤器都应附带清晰、完整的文档，以确保其功能、配置和使用方法得到充分说明。

56
plugins/filters/async-context-compression/async_context_compression.py
View File

@@ -2,8 +2,8 @@
title: Async Context Compression
id: async_context_compression
author: Fu-Jie
author_url: https://github.com/Fu-Jie
funding_url: https://github.com/Fu-Jie/awesome-openwebui
author_url: https://github.com/Fu-Jie/awesome-openwebui
funding_url: https://github.com/open-webui
description: Reduces token consumption in long conversations while maintaining coherence through intelligent summarization and message compression.
version: 1.1.3
openwebui_id: b1655bc8-6de9-4cad-8cb5-a6f7829a02ce
@@ -621,25 +621,41 @@ class Filter:
"max_context_tokens": self.valves.max_context_tokens,
}
def _extract_chat_id(self, body: dict, metadata: Optional[dict]) -> str:
"""Extract chat_id from body or metadata."""
def _get_chat_context(
self, body: dict, __metadata__: Optional[dict] = None
) -> Dict[str, str]:
"""
Unified extraction of chat context information (chat_id, message_id).
Prioritizes extraction from body, then metadata.
"""
chat_id = ""
message_id = ""
# 1. Try to get from body
if isinstance(body, dict):
chat_id = body.get("chat_id")
if isinstance(chat_id, str) and chat_id.strip():
return chat_id.strip()
chat_id = body.get("chat_id", "")
message_id = body.get("id", "") # message_id is usually 'id' in body
body_metadata = body.get("metadata", {})
if isinstance(body_metadata, dict):
chat_id = body_metadata.get("chat_id")
if isinstance(chat_id, str) and chat_id.strip():
return chat_id.strip()
# Check body.metadata as fallback
if not chat_id or not message_id:
body_metadata = body.get("metadata", {})
if isinstance(body_metadata, dict):
if not chat_id:
chat_id = body_metadata.get("chat_id", "")
if not message_id:
message_id = body_metadata.get("message_id", "")
if isinstance(metadata, dict):
chat_id = metadata.get("chat_id")
if isinstance(chat_id, str) and chat_id.strip():
return chat_id.strip()
# 2. Try to get from __metadata__ (as supplement)
if __metadata__ and isinstance(__metadata__, dict):
if not chat_id:
chat_id = __metadata__.get("chat_id", "")
if not message_id:
message_id = __metadata__.get("message_id", "")
return ""
return {
"chat_id": str(chat_id).strip(),
"message_id": str(message_id).strip(),
}
async def _emit_debug_log(
self,
@@ -750,7 +766,8 @@ class Filter:
Compression Strategy: Only responsible for injecting existing summaries, no Token calculation.
"""
messages = body.get("messages", [])
chat_id = self._extract_chat_id(body, __metadata__)
chat_ctx = self._get_chat_context(body, __metadata__)
chat_id = chat_ctx["chat_id"]
if not chat_id:
await self._log(
@@ -867,7 +884,8 @@ class Filter:
Executed after the LLM response is complete.
Calculates Token count in the background and triggers summary generation (does not block current response, does not affect content output).
"""
chat_id = self._extract_chat_id(body, __metadata__)
chat_ctx = self._get_chat_context(body, __metadata__)
chat_id = chat_ctx["chat_id"]
if not chat_id:
await self._log(
"[Outlet] ❌ Missing chat_id in metadata, skipping compression",

46
plugins/filters/async-context-compression/async_context_compression_cn.py
View File

@@ -2,8 +2,8 @@
title: 异步上下文压缩
id: async_context_compression
author: Fu-Jie
author_url: https://github.com/Fu-Jie
funding_url: https://github.com/Fu-Jie/awesome-openwebui
author_url: https://github.com/Fu-Jie/awesome-openwebui
funding_url: https://github.com/open-webui
description: 通过智能摘要和消息压缩，降低长对话的 token 消耗，同时保持对话连贯性。
version: 1.1.3
openwebui_id: 5c0617cb-a9e4-4bd6-a440-d276534ebd18
@@ -472,6 +472,42 @@ class Filter:
"max_context_tokens": self.valves.max_context_tokens,
}
def _get_chat_context(
self, body: dict, __metadata__: Optional[dict] = None
) -> Dict[str, str]:
"""
统一提取聊天上下文信息 (chat_id, message_id)。
优先从 body 中提取，其次从 metadata 中提取。
"""
chat_id = ""
message_id = ""
# 1. 尝试从 body 获取
if isinstance(body, dict):
chat_id = body.get("chat_id", "")
message_id = body.get("id", "") # message_id 在 body 中通常是 id
# 再次检查 body.metadata
if not chat_id or not message_id:
body_metadata = body.get("metadata", {})
if isinstance(body_metadata, dict):
if not chat_id:
chat_id = body_metadata.get("chat_id", "")
if not message_id:
message_id = body_metadata.get("message_id", "")
# 2. 尝试从 __metadata__ 获取 (作为补充)
if __metadata__ and isinstance(__metadata__, dict):
if not chat_id:
chat_id = __metadata__.get("chat_id", "")
if not message_id:
message_id = __metadata__.get("message_id", "")
return {
"chat_id": str(chat_id).strip(),
"message_id": str(message_id).strip(),
}
async def _emit_debug_log(
self,
__event_call__,
@@ -581,7 +617,8 @@ class Filter:
压缩策略：只负责注入已有的摘要，不进行 Token 计算
"""
messages = body.get("messages", [])
chat_id = __metadata__["chat_id"]
chat_ctx = self._get_chat_context(body, __metadata__)
chat_id = chat_ctx["chat_id"]
if self.valves.debug_mode or self.valves.show_debug_log:
await self._log(
@@ -690,7 +727,8 @@ class Filter:
在 LLM 响应完成后执行
在后台计算 Token 数并触发摘要生成（不阻塞当前响应，不影响内容输出）
"""
chat_id = __metadata__["chat_id"]
chat_ctx = self._get_chat_context(body, __metadata__)
chat_id = chat_ctx["chat_id"]
model = body.get("model") or ""
# 直接计算目标压缩进度

9
plugins/filters/multi_model_context_merger.py
View File

@@ -1,3 +1,12 @@
"""
title: Multi-Model Context Merger
author: Fu-Jie
author_url: https://github.com/Fu-Jie/awesome-openwebui
funding_url: https://github.com/Fu-Jie/awesome-openwebui
version: 0.1.0
description: Automatically merges context from multiple model responses in the previous turn.
"""
import asyncio
from typing import List, Optional, Dict
from pydantic import BaseModel, Field