Merge commit '652499ed81bf1c8629073b5589dbd6f5ec014b37'

Author: L-jasmine

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "echokit_server"
-version = "0.2.5"
+version = "0.3.0"
 edition = "2021"
 
 [dependencies]

docker/server-vad/config.toml

@@ -2,12 +2,14 @@ addr = "0.0.0.0:8080"
 hello_wav = "hello.wav"
 
 [tts]
-platform = "Groq"
+platform = "openai"
+url = "https://api.groq.com/openai/v1/audio/speech"
 model = "playai-tts"
 api_key = "gsk_ABCD"
 voice = "Fritz-PlayAI"
 
 [asr]
+platform = "openai"
 url = "https://api.groq.com/openai/v1/audio/transcriptions"
 api_key = "gsk_ABCD"
 model = "whisper-large-v3"
@@ -19,7 +21,8 @@ vad_url = "http://localhost:8000/v1/audio/vad"
 # vad_realtime_url = "ws://localhost:8000/v1/audio/realtime_vad"
 
 [llm]
-llm_chat_url = "https://api.groq.com/openai/v1/chat/completions"
+platform = "openai_chat"
+url = "https://api.groq.com/openai/v1/chat/completions"
 api_key = "gsk_ABCD"
 model = "openai/gpt-oss-20b"
 history = 5

docker/server/config.toml

@@ -2,20 +2,23 @@ addr = "0.0.0.0:8080"
 hello_wav = "hello.wav"
 
 [tts]
-platform = "Groq"
+platform = "openai"
+url = "https://api.groq.com/openai/v1/audio/speech"
 model = "playai-tts"
 api_key = "gsk_ABCD"
 voice = "Fritz-PlayAI"
 
 [asr]
+platform = "openai"
 url = "https://api.groq.com/openai/v1/audio/transcriptions"
 api_key = "gsk_ABCD"
 model = "whisper-large-v3"
 lang = "en"
 prompt = "Hello\n你好\n(noise)\n(bgm)\n(silence)\n"
 
 [llm]
-llm_chat_url = "https://api.groq.com/openai/v1/chat/completions"
+platform = "openai_chat"
+url = "https://api.groq.com/openai/v1/chat/completions"
 api_key = "gsk_ABCD"
 model = "openai/gpt-oss-20b"
 history = 5

examples/alibailian/config.toml

@@ -1,56 +1,51 @@
-addr = "0.0.0.0:8070"
+addr = "0.0.0.0:8080"
 hello_wav = "hello.wav"
 
+# Get your API key from https://bailian.console.aliyun.com/
+
 [asr]
-# platform = "paraformer_v2"
-platform = "ParaformerV2"
-paraformer_token = "API Key"
+platform = "paraformer_v2"
+url = "wss://dashscope.aliyuncs.com/api-ws/v1/inference"
+paraformer_token = "sk-API-KEY"
 
-# Get your API key from https://bailian.console.aliyun.com/
 
 [tts]
-# platform = "cosyvoice"
-platform = "CosyVoice"
-token = "API Key"
+platform = "cosyvoice"
+url = "wss://dashscope.aliyuncs.com/api-ws/v1/inference"
+token = "sk-API-KEY"
 speaker = "longhua_v2"
 
-# Get your API key from https://bailian.console.aliyun.com/
 # Supported platforms: cosyvoice-v2 (default) and cosyvoice-v1
 # Get speaker list from https://help.aliyun.com/zh/model-studio/cosyvoice-java-sdk#722dd7ca66a6x
 
 [llm]
-platform = "chat"
+platform = "openai_chat"
 url = "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions"
-api_key = "API-key"
+api_key = "sk-API-KEY"
 model = "qwen-plus"
 history = 5
 
-# Get your API key from https://bailian.console.aliyun.com/
-# Any text generation models is supported.
-
+[llm.extra]
+enable_search = true
 
 [[llm.sys_prompts]]
 role = "system"
 content = """
-你叫胡桃，是一个优秀的翻译官。你现在的任务是，把我给你的中文翻译成英文，并且用英文回答我。
+You are a helpful assistant. Answer truthfully and concisely.
 
-你说话时必须满足以下格式
-第一行是你当前的状态或者要执行的动作，第二行开始是你的对话内容
+- NEVER use bullet points
+- NEVER use tables
+- Answer in complete sentences as if you are in a conversation.
+- Use the web_search tool if you need information about current events such as news, political figures, stock prices, and crypto prices.
 
-比如：
-[翻译]
-这句话的翻译是 "I am a translator"。
-"""
+------
 
-[[llm.sys_prompts]]
-role = "user"
-content = """
-我是一个翻译官
-"""
+您是一位乐于助人的助手。请如实简洁地回答问题。
+
+- 切勿使用列表
+- 切勿使用表格
+- 请使用完整的句子回答，就像在对话一样。
+- 如果您需要了解时事信息，例如新闻、政治人物、股票价格和加密货币价格，请使用 web_search tool。
 
-[[llm.sys_prompts]]
-role = "assistant"
-content = """
-[翻译]
-这句话的翻译是 "I am a translator"。
 """
+

examples/background_gaia.gif

@@ -3,13 +3,13 @@ hello_wav = "hello.wav"
 
 # Requires a local gsv_tts server at port 9094: https://github.com/second-state/gsv_tts
 [tts]
-platform = "StreamGSV"
+platform = "stream_gsv"
 url = "http://localhost:9094/v1/audio/stream_speech"
 speaker = "cooper"
 
 # Requires a local Whisper API server at port 9092: https://llamaedge.com/docs/ai-models/speech-to-text/quick-start-whisper
 [asr]
-platform = "whisper"
+platform = "openai"
 url = "http://localhost:9092/v1/audio/transcriptions"
 lang = "auto"
 # Requires a local Silero VAD server at port 9093: https://github.com/second-state/silero_vad_server
@@ -18,7 +18,7 @@ vad_url = "http://localhost:9093/v1/audio/vad"
 
 # Requires a local LlamaEdge API server at port 9091: https://llamaedge.com/docs/ai-models/llm/quick-start-llm
 [llm]
-platform = "chat"
+platform = "openai_chat"
 url = "http://localhost:9091/v1/chat/completions"
 api_key = "Bearer gaia-1234"
 model = "default"

examples/background_gosim.gif

@@ -2,21 +2,21 @@ addr = "0.0.0.0:9090"
 hello_wav = "hello.wav"
 
 [tts]
-platform = "StreamGSV"
+platform = "stream_gsv"
 url = "http://localhost:9094/v1/audio/stream_speech"
 speaker = "cooper"
 
 [asr]
-platform = "whisper"
+platform = "openai"
 url = "http://localhost:9092/v1/audio/transcriptions"
 lang = "auto"
 # vad_url = "http://localhost:9093/v1/audio/vad"
 vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
 
 [llm]
-platform = "chat"
+platform = "openai_chat"
 url = "http://localhost:9091/v1/chat/completions"
-api_key = "Bearer gaia-1234"
+api_key = "gaia-1234"
 history = 5
 
 [[llm.sys_prompts]]

examples/background_wasmedge.gif

@@ -2,21 +2,21 @@ addr = "0.0.0.0:9090"
 hello_wav = "hello.wav"
 
 [tts]
-platform = "StreamGSV"
+platform = "stream_gsv"
 url = "http://localhost:9094/v1/audio/stream_speech"
 speaker = "cooper"
 
 [asr]
-platform = "whisper"
+platform = "openai"
 url = "http://localhost:9092/v1/audio/transcriptions"
 lang = "auto"
 # vad_url = "http://localhost:9093/v1/audio/vad"
 vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
 
 [llm]
-platform = "chat"
+platform = "openai_chat"
 url = "http://localhost:9091/v1/chat/completions"
-api_key = "Bearer gaia-1234"
+api_key = "gaia-1234"
 history = 5
 
 [[llm.sys_prompts]]