Hass/xiaozhi-esp32-server
1
0
Fork 0
mirror of https://github.com/xinnan-tech/xiaozhi-esp32-server.git synced 2026-07-28 01:53:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into test-pr-sherpa-asr

Browse Source
This commit is contained in:
Huang
2025-03-19 23:21:23 +08:00
committed by GitHub
parent 08e57936fc 0c2b194444
commit a4b4f491d2
50 changed files with 1410 additions and 602 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main/xiaozhi-server/core/providers/llm/dify/dify.py
+47 -14
View File
@@ -9,6 +9,7 @@ logger = setup_logging()
class LLMProvider(LLMProviderBase):
def __init__(self, config):
self.api_key = config["api_key"]
self.mode = config.get("mode", "chat-messages")
self.base_url = config.get("base_url", "https://api.dify.ai/v1").rstrip('/')
self.session_conversation_map = {} # 存储session_id和conversation_id的映射
@@ -19,27 +20,59 @@ class LLMProvider(LLMProviderBase):
conversation_id = self.session_conversation_map.get(session_id)
# 发起流式请求
with requests.post(
f"{self.base_url}/chat-messages",
headers={"Authorization": f"Bearer {self.api_key}"},
json={
if self.mode == "chat-messages":
request_json = {
"query": last_msg["content"],
"response_mode": "streaming",
"user": session_id,
"inputs": {},
"conversation_id": conversation_id
},
}
elif self.mode == "workflows/run":
request_json = {
"inputs": {"query": last_msg["content"]},
"response_mode": "streaming",
"user": session_id
}
elif self.mode == "completion-messages":
request_json = {
"inputs": {"query": last_msg["content"]},
"response_mode": "streaming",
"user": session_id
}
with requests.post(
f"{self.base_url}/{self.mode}",
headers={"Authorization": f"Bearer {self.api_key}"},
json=request_json,
stream=True
) as r:
for line in r.iter_lines():
if line.startswith(b'data: '):
event = json.loads(line[6:])
# 如果没有找到conversation_id，则获取此次conversation_id
if not conversation_id:
conversation_id = event.get('conversation_id')
self.session_conversation_map[session_id] = conversation_id # 更新映射
if event.get('answer'):
yield event['answer']
if self.mode == "chat-messages":
for line in r.iter_lines():
if line.startswith(b'data: '):
event = json.loads(line[6:])
# 如果没有找到conversation_id，则获取此次conversation_id
if not conversation_id:
conversation_id = event.get('conversation_id')
self.session_conversation_map[session_id] = conversation_id # 更新映射
if event.get('answer'):
yield event['answer']
elif self.mode == "workflows/run":
for line in r.iter_lines():
# logger.bind(tag=TAG).info(f"chat message response: {line}")
if line.startswith(b'data: '):
event = json.loads(line[6:])
if event.get('event') == "workflow_finished":
if event['data']['status'] == "succeeded":
yield event['data']['outputs']['answer']
else:
yield "【服务响应异常】"
elif self.mode == "completion-messages":
for line in r.iter_lines():
if line.startswith(b'data: '):
event = json.loads(line[6:])
if event.get('answer'):
yield event['answer']
except Exception as e:
logger.bind(tag=TAG).error(f"Error in response generation: {e}")
main/xiaozhi-server/core/providers/tts/base.py
+1 -1
View File
@@ -13,7 +13,7 @@ logger = setup_logging()
class TTSProviderBase(ABC):
def __init__(self, config, delete_audio_file):
self.delete_audio_file = delete_audio_file
self.output_file = config.get("output_file")
self.output_file = config.get("output_dir")
@abstractmethod
def generate_filename(self):
main/xiaozhi-server/core/providers/tts/custom.py
+1 -1
View File
@@ -15,7 +15,7 @@ class TTSProvider(TTSProviderBase):
self.headers = config.get("headers", {})
self.params = config.get("params")
self.format = config.get("format", "wav")
self.output_file = config.get("output_file", "tmp/")
self.output_file = config.get("output_dir", "tmp/")
def generate_filename(self):
return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}.{self.format}")
main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py
+1 -1
View File
@@ -22,7 +22,7 @@ class TTSProvider(TTSProviderBase):
self.cut_punc = config.get("cut_punc","")
self.speed = config.get("speed", 1.0)
self.inp_refs = config.get("inp_refs",[])
self.sample_steps = config.get("inp_refs",32)
self.sample_steps = config.get("sample_steps",32)
self.if_sr = config.get("if_sr",False)
main/xiaozhi-server/core/providers/tts/openai.py
+1 -1
View File
@@ -14,7 +14,7 @@ class TTSProvider(TTSProviderBase):
self.voice = config.get("voice", "alloy")
self.response_format = "wav"
self.speed = config.get("speed", 1.0)
self.output_file = config.get("output_file", "tmp/")
self.output_file = config.get("output_dir", "tmp/")
check_model_key("TTS", self.api_key)
def generate_filename(self, extension=".wav"):
main/xiaozhi-server/core/providers/tts/ttson.py
+1 -1
View File
@@ -17,7 +17,7 @@ class TTSProvider(TTSProviderBase):
self.volume_change_dB = config.get("volume_change_dB", 0)
self.speed_factor = config.get("speed_factor", 1)
self.stream = config.get("stream", False)
self.output_file = config.get("output_file")
self.output_file = config.get("output_dir")
self.pitch_factor = config.get("pitch_factor", 0)
self.format = config.get("format", "mp3")
self.emotion = config.get("emotion", 1)