Compare commits

...

3 Commits

Author SHA1 Message Date
Soulter
e9be8cf69f chore: bump version to 4.7.4 2025-12-01 18:42:07 +08:00
Soulter
31d53edb9d refactor: standardize provider test method implementation
- Updated the `test` method in all provider classes to remove return values and raise exceptions for failure cases, enhancing clarity and consistency.
- Adjusted related logic in the dashboard and command routes to align with the new `test` method behavior, simplifying error handling.
2025-12-01 18:37:08 +08:00
Soulter
2ba0460f19 feat: introduce file extract capability (#3870)
* feat: introduce file extract capability

powered by MoonshotAI

* fix: correct indentation in default configuration file

* fix: add error handling for file extract application in InternalAgentSubStage

* fix: update file name handling in InternalAgentSubStage to correctly associate file names with extracted content

* feat: add condition settings for local agent runner in default configuration

* fix: enhance file naming logic in File component and update prompt handling in InternalAgentSubStage
2025-12-01 18:12:39 +08:00
13 changed files with 231 additions and 88 deletions

View File

@@ -1 +1 @@
__version__ = "4.7.3"
__version__ = "4.7.4"

View File

@@ -4,7 +4,7 @@ import os
from astrbot.core.utils.astrbot_path import get_astrbot_data_path
VERSION = "4.7.3"
VERSION = "4.7.4"
DB_PATH = os.path.join(get_astrbot_data_path(), "data_v4.db")
# 默认配置
@@ -76,6 +76,11 @@ DEFAULT_CONFIG = {
"reachability_check": False,
"max_agent_step": 30,
"tool_call_timeout": 60,
"file_extract": {
"enable": False,
"provider": "moonshotai",
"moonshotai_api_key": "",
},
},
"provider_stt_settings": {
"enable": False,
@@ -2069,6 +2074,20 @@ CONFIG_METADATA_2 = {
"tool_call_timeout": {
"type": "int",
},
"file_extract": {
"type": "object",
"items": {
"enable": {
"type": "bool",
},
"provider": {
"type": "string",
},
"moonshotai_api_key": {
"type": "string",
},
},
},
},
},
"provider_stt_settings": {
@@ -2403,6 +2422,36 @@ CONFIG_METADATA_3 = {
"provider_settings.enable": True,
},
},
# "file_extract": {
# "description": "文档解析能力 [beta]",
# "type": "object",
# "items": {
# "provider_settings.file_extract.enable": {
# "description": "启用文档解析能力",
# "type": "bool",
# },
# "provider_settings.file_extract.provider": {
# "description": "文档解析提供商",
# "type": "string",
# "options": ["moonshotai"],
# "condition": {
# "provider_settings.file_extract.enable": True,
# },
# },
# "provider_settings.file_extract.moonshotai_api_key": {
# "description": "Moonshot AI API Key",
# "type": "string",
# "condition": {
# "provider_settings.file_extract.provider": "moonshotai",
# "provider_settings.file_extract.enable": True,
# },
# },
# },
# "condition": {
# "provider_settings.agent_runner_type": "local",
# "provider_settings.enable": True,
# },
# },
"others": {
"description": "其他配置",
"type": "object",

View File

@@ -722,7 +722,12 @@ class File(BaseMessageComponent):
"""下载文件"""
download_dir = os.path.join(get_astrbot_data_path(), "temp")
os.makedirs(download_dir, exist_ok=True)
file_path = os.path.join(download_dir, f"{uuid.uuid4().hex}")
if self.name:
name, ext = os.path.splitext(self.name)
filename = f"{name}_{uuid.uuid4().hex[:8]}{ext}"
else:
filename = f"{uuid.uuid4().hex}"
file_path = os.path.join(download_dir, filename)
await download_file(self.url, file_path)
self.file_ = os.path.abspath(file_path)

View File

@@ -9,7 +9,7 @@ from astrbot.core import logger
from astrbot.core.agent.tool import ToolSet
from astrbot.core.astr_agent_context import AstrAgentContext
from astrbot.core.conversation_mgr import Conversation
from astrbot.core.message.components import Image
from astrbot.core.message.components import File, Image, Reply
from astrbot.core.message.message_event_result import (
MessageChain,
MessageEventResult,
@@ -22,6 +22,7 @@ from astrbot.core.provider.entities import (
ProviderRequest,
)
from astrbot.core.star.star_handler import EventType, star_map
from astrbot.core.utils.file_extract import extract_file_moonshotai
from astrbot.core.utils.metrics import Metric
from astrbot.core.utils.session_lock import session_lock_manager
@@ -56,6 +57,13 @@ class InternalAgentSubStage(Stage):
self.show_reasoning = settings.get("display_reasoning_text", False)
self.kb_agentic_mode: bool = conf.get("kb_agentic_mode", False)
file_extract_conf: dict = settings.get("file_extract", {})
self.file_extract_enabled: bool = file_extract_conf.get("enable", False)
self.file_extract_prov: str = file_extract_conf.get("provider", "moonshotai")
self.file_extract_msh_api_key: str = file_extract_conf.get(
"moonshotai_api_key", ""
)
self.conv_manager = ctx.plugin_manager.context.conversation_manager
def _select_provider(self, event: AstrMessageEvent):
@@ -114,6 +122,50 @@ class InternalAgentSubStage(Stage):
req.func_tool = ToolSet()
req.func_tool.add_tool(KNOWLEDGE_BASE_QUERY_TOOL)
async def _apply_file_extract(
self,
event: AstrMessageEvent,
req: ProviderRequest,
):
"""Apply file extract to the provider request"""
file_paths = []
file_names = []
for comp in event.message_obj.message:
if isinstance(comp, File):
file_paths.append(await comp.get_file())
file_names.append(comp.name)
elif isinstance(comp, Reply) and comp.chain:
for reply_comp in comp.chain:
if isinstance(reply_comp, File):
file_paths.append(await reply_comp.get_file())
file_names.append(reply_comp.name)
if not file_paths:
return
if not req.prompt:
req.prompt = "总结一下文件里面讲了什么?"
if self.file_extract_prov == "moonshotai":
if not self.file_extract_msh_api_key:
logger.error("Moonshot AI API key for file extract is not set")
return
file_contents = await asyncio.gather(
*[
extract_file_moonshotai(file_path, self.file_extract_msh_api_key)
for file_path in file_paths
]
)
else:
logger.error(f"Unsupported file extract provider: {self.file_extract_prov}")
return
# add file extract results to contexts
for file_content, file_name in zip(file_contents, file_names):
req.contexts.append(
{
"role": "system",
"content": f"File Extract Results of user uploaded files:\n{file_content}\nFile Name: {file_name or 'Unknown'}",
},
)
def _truncate_contexts(
self,
contexts: list[dict],
@@ -346,6 +398,17 @@ class InternalAgentSubStage(Stage):
event.set_extra("provider_request", req)
# fix contexts json str
if isinstance(req.contexts, str):
req.contexts = json.loads(req.contexts)
# apply file extract
if self.file_extract_enabled:
try:
await self._apply_file_extract(event, req)
except Exception as e:
logger.error(f"Error occurred while applying file extract: {e}")
if not req.prompt and not req.image_urls:
return
@@ -356,10 +419,6 @@ class InternalAgentSubStage(Stage):
# apply knowledge base feature
await self._apply_kb(event, req)
# fix contexts json str
if isinstance(req.contexts, str):
req.contexts = json.loads(req.contexts)
# truncate contexts to fit max length
if req.contexts:
req.contexts = self._truncate_contexts(req.contexts)

View File

@@ -381,7 +381,9 @@ class TelegramPlatformAdapter(Platform):
f"Telegram document file_path is None, cannot save the file {file_name}.",
)
else:
message.message.append(Comp.File(file=file_path, name=file_name))
message.message.append(
Comp.File(file=file_path, name=file_name, url=file_path)
)
elif update.message.video:
file = await update.message.video.get_file()

View File

@@ -45,13 +45,13 @@ class AbstractProvider(abc.ABC):
)
return meta
async def test(self) -> bool:
async def test(self):
"""test the provider is a
Returns:
bool: the provider is available
raises:
Exception: if the provider is not available
"""
return True
...
class Provider(AbstractProvider):
@@ -175,15 +175,11 @@ class Provider(AbstractProvider):
return dicts
async def test(self, timeout: float = 45.0) -> bool:
try:
response = await asyncio.wait_for(
self.text_chat(prompt="REPLY `PONG` ONLY"),
timeout=timeout,
)
return response is not None
except Exception:
return False
async def test(self, timeout: float = 45.0):
await asyncio.wait_for(
self.text_chat(prompt="REPLY `PONG` ONLY"),
timeout=timeout,
)
class STTProvider(AbstractProvider):
@@ -197,19 +193,13 @@ class STTProvider(AbstractProvider):
"""获取音频的文本"""
raise NotImplementedError
async def test(self) -> bool:
try:
sample_audio_path = os.path.join(
get_astrbot_path(),
"samples",
"stt_health_check.wav",
)
if not os.path.exists(sample_audio_path):
return False
text_result = await self.get_text(sample_audio_path)
return isinstance(text_result, str) and bool(text_result)
except Exception:
return False
async def test(self):
sample_audio_path = os.path.join(
get_astrbot_path(),
"samples",
"stt_health_check.wav",
)
await self.get_text(sample_audio_path)
class TTSProvider(AbstractProvider):
@@ -223,12 +213,8 @@ class TTSProvider(AbstractProvider):
"""获取文本的音频,返回音频文件路径"""
raise NotImplementedError
async def test(self) -> bool:
try:
audio_result = await self.get_audio("hi")
return isinstance(audio_result, str) and bool(audio_result)
except Exception:
return False
async def test(self):
await self.get_audio("hi")
class EmbeddingProvider(AbstractProvider):
@@ -252,14 +238,8 @@ class EmbeddingProvider(AbstractProvider):
"""获取向量的维度"""
...
async def test(self) -> bool:
try:
embedding_result = await self.get_embedding("health_check")
return isinstance(embedding_result, list) and (
not embedding_result or isinstance(embedding_result[0], float)
)
except Exception:
return False
async def test(self):
await self.get_embedding("astrbot")
async def get_embeddings_batch(
self,
@@ -345,9 +325,7 @@ class RerankProvider(AbstractProvider):
"""获取查询和文档的重排序分数"""
...
async def test(self) -> bool:
try:
await self.rerank("Apple", documents=["apple", "banana"])
return True
except Exception:
return False
async def test(self):
result = await self.rerank("Apple", documents=["apple", "banana"])
if not result:
raise Exception("Rerank provider test failed, no results returned")

View File

@@ -0,0 +1,23 @@
from pathlib import Path
from openai import AsyncOpenAI
async def extract_file_moonshotai(file_path: str, api_key: str) -> str:
"""Extract text from a file using Moonshot AI API"""
"""
Args:
file_path: The path to the file to extract text from
api_key: The API key to use to extract text from the file
Returns:
The text extracted from the file
"""
client = AsyncOpenAI(
api_key=api_key,
base_url="https://api.moonshot.cn/v1",
)
file_object = await client.files.create(
file=Path(file_path),
purpose="file-extract", # type: ignore
)
return (await client.files.content(file_id=file_object.id)).text

View File

@@ -354,17 +354,11 @@ class ConfigRoute(Route):
)
try:
result = await provider.test()
if result:
status_info["status"] = "available"
logger.info(
f"Provider {status_info['name']} (ID: {status_info['id']}) is available.",
)
else:
status_info["error"] = "Provider test returned False."
logger.warning(
f"Provider {status_info['name']} (ID: {status_info['id']}) test returned False.",
)
await provider.test()
status_info["status"] = "available"
logger.info(
f"Provider {status_info['name']} (ID: {status_info['id']}) is available.",
)
except Exception as e:
error_message = str(e)
status_info["error"] = error_message

7
changelogs/v4.7.4.md Normal file
View File

@@ -0,0 +1,7 @@
## What's Changed
1. 修复assistant message 中 tool_call 存在但 content 不存在时,导致验证错误的问题 ([#3862](https://github.com/AstrBotDevs/AstrBot/issues/3862))
2. 修复fix: aiocqhttp 适配器 NapCat 文件名获取为空 ([#3853](https://github.com/AstrBotDevs/AstrBot/issues/3853))
3. 新增:升级所有插件按钮
4. 新增:/provider 指令支持同时测试提供商可用性
5. 优化:主动回复的 prompt

View File

@@ -109,6 +109,22 @@
}
}
},
"file_extract": {
"description": "File Extract",
"provider_settings": {
"file_extract": {
"enable": {
"description": "Enable File Extract"
},
"provider": {
"description": "File Extract Provider"
},
"moonshotai_api_key": {
"description": "Moonshot AI API Key"
}
}
}
},
"others": {
"description": "Other Settings",
"provider_settings": {

View File

@@ -11,7 +11,12 @@
},
"agent_runner_type": {
"description": "执行器",
"labels": ["内置 Agent", "Dify", "Coze", "阿里云百炼应用"]
"labels": [
"内置 Agent",
"Dify",
"Coze",
"阿里云百炼应用"
]
},
"coze_agent_runner_provider_id": {
"description": "Coze Agent 执行器提供商 ID"
@@ -109,6 +114,22 @@
}
}
},
"file_extract": {
"description": "文档解析能力",
"provider_settings": {
"file_extract": {
"enable": {
"description": "启用文档解析能力"
},
"provider": {
"description": "文档解析提供商"
},
"moonshotai_api_key": {
"description": "Moonshot AI API Key"
}
}
}
},
"others": {
"description": "其他配置",
"provider_settings": {
@@ -142,7 +163,10 @@
"unsupported_streaming_strategy": {
"description": "不支持流式回复的平台",
"hint": "选择在不支持流式回复的平台上的处理方式。实时分段回复会在系统接收流式响应检测到诸如标点符号等分段点时,立即发送当前已接收的内容",
"labels": ["实时分段回复", "关闭流式回复"]
"labels": [
"实时分段回复",
"关闭流式回复"
]
},
"max_context_length": {
"description": "最多携带对话轮数",
@@ -457,4 +481,4 @@
}
}
}
}
}

View File

@@ -34,25 +34,11 @@ class ProviderCommands:
provider_capability_type = meta.provider_type
try:
result = await provider.test()
if result:
return True, None, None
await provider.test()
return True, None, None
except Exception as e:
err_code = "TEST_FAILED"
err_reason = "Provider test returned False"
self._log_reachability_failure(
provider, provider_capability_type, err_code, err_reason
)
return False, err_code, err_reason
except Exception as exc:
err_code = (
getattr(exc, "status_code", None)
or getattr(exc, "code", None)
or getattr(exc, "error_code", None)
)
err_reason = str(exc)
if not err_code:
err_code = exc.__class__.__name__
err_reason = str(e)
self._log_reachability_failure(
provider, provider_capability_type, err_code, err_reason
)

View File

@@ -1,6 +1,6 @@
[project]
name = "AstrBot"
version = "4.7.3"
version = "4.7.4"
description = "Easy-to-use multi-platform LLM chatbot and development framework"
readme = "README.md"
requires-python = ">=3.10"