achatbot
achatbot factory, create chat bots with vad,turn, asr, llm(tools)/mllm/audio-llm/omni-llm, tts, avatar, ocr, detect object etc..
- achatbot-go (main/sub agent)
Features
Model Context Protocol(MCP)
Agent2Agent (A2A) ProtocolDesign
apipeline design
- ⭐️ pipeline design ⭐️
achatbot design
Install
pypi
python3 -m venv .venv_achatbot
source .venv_achatbot/bin/activate
pip install achatbot
# optional-dependencies e.g.
pip install "achatbot[fastapi_bot_server]"
local
git clone --recursive https://github.com/ai-bot-pro/chat-bot.git
cd chat-bot
python3 -m venv .venv_achatbot
source .venv_achatbot/bin/activate
bash scripts/pypi_achatbot.sh dev
# optional-dependencies e.g.
pip install "dist/achatbot-{$version}-py3-none-any.whl[fastapi_bot_server]"
run local lite avatar chat bot
# install dependencies (replace $version) (if use cpu(default) install lite_avatar)
pip install "dist/achatbot-{$version}-py3-none-any.whl[fastapi_bot_server,livekit,livekit-api,daily,agora,silero_vad_analyzer,sense_voice_asr,openai_llm_processor,google_llm_processor,litellm_processor,together_ai,tts_edge,lite_avatar]"
# install dependencies (replace $version) (if use gpu(cuda) install lite_avatar_gpu)
pip install "dist/achatbot-{$version}-py3-none-any.whl[fastapi_bot_server,livekit,livekit-api,daily,agora,silero_vad_analyzer,sense_voice_asr,openai_llm_processor,google_llm_processor,litellm_processor,together_ai,tts_edge,lite_avatar_gpu]"
# download model weights
huggingface-cli download weege007/liteavatar --local-dir ./models/weege007/liteavatar
huggingface-cli download FunAudioLLM/SenseVoiceSmall --local-dir ./models/FunAudioLLM/SenseVoiceSmall
# run local lite-avatar chat bot
python -m src.cmd.bots.main -f config/bots/daily_liteavatar_echo_bot.json
python -m src.cmd.bots.main -f config/bots/daily_liteavatar_chat_bot.json
More details: https://github.com/ai-bot-pro/achatbot/pull/161
run local lam_audio2expression avatar chat bot
# install dependencies (replace $version)
pip install "dist/achatbot-{$version}-py3-none-any.whl[fastapi_bot_server,silero_vad_analyzer,sense_voice_asr,openai_llm_processor,google_llm_processor,litellm_processor,together_ai,tts_edge,lam_audio2expression_avatar]"
pip install spleeter==2.4.2
pip install typing_extensions==4.14.0 aiortc==1.13.0 transformers==4.36.2 protobuf==5.29.4
# download model weights
wget https://virutalbuy-public.oss-cn-hangzhou.aliyuncs.com/share/aigc3d/data/LAM/LAM_audio2exp_streaming.tar -P ./models/LAM_audio2exp/
tar -xzvf ./models/LAM_audio2exp/LAM_audio2exp_streaming.tar -C ./models/LAM_audio2exp && rm ./models/LAM_audio2exp/LAM_audio2exp_streaming.tar
git clone --depth 1 https://www.modelscope.cn/AI-ModelScope/wav2vec2-base-960h.git ./models/facebook/wav2vec2-base-960h
huggingface-cli download FunAudioLLM/SenseVoiceSmall --local-dir ./models/FunAudioLLM/SenseVoiceSmall
# run http signaling service + webrtc + websocket local lam_audio2expression-avatar chat bot
python -m src.cmd.webrtc_websocket.fastapi_ws_signaling_bot_serve -f config/bots/small_webrtc_fastapi_websocket_avatar_echo_bot.json
python -m src.cmd.webrtc_websocket.fastapi_ws_signaling_bot_serve -f config/bots/small_webrtc_fastapi_websocket_avatar_chat_bot.json
# run http signaling service + webrtc + websocket voice avatar agent web ui
cd ui/webrtc_websocket/lam_audio2expression_avatar_ts && npm install && npm run dev
# run websocket signaling service + webrtc + websocket local lam_audio2expression-avatar chat bot
python -m src.cmd.webrtc_websocket.fastapi_ws_signaling_bot_serve_v2 -f config/bots/small_webrtc_fastapi_websocket_avatar_echo_bot.json
python -m src.cmd.webrtc_websocket.fastapi_ws_signaling_bot_serve_v2 -f config/bots/small_webrtc_fastapi_websocket_avatar_chat_bot.json
# run websocket signaling service + webrtc + websocket voice avatar agent web ui
cd ui/webrtc_websocket/lam_audio2expression_avatar_ts_v2 && npm install && npm run dev
More details: https://github.com/ai-bot-pro/achatbot/pull/164 and https://github.com/ai-bot-pro/achatbot/pull/206 | online lam_audio2expression avatar: https://avatar-2lm.pages.dev/
Run chat bots
License
achatbot is released under the BSD 3 license. (Additional code in this distribution is covered by the MIT and Apache Open Source licenses.) However you may have other legal obligations that govern your use of content, such as the terms of service for third-party models.
1 maintainer
Metadata
1 maintainer
Release files for achatbot 0.0.33.post1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| achatbot-0.0.33.post1.tar.gz | 22.7 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| achatbot-0.0.33.post1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 28.5 MB
Release files / achatbot-0.0.33.post1.tar.gz
| Download URL | achatbot-0.0.33.post1.tar.gz |
|---|---|
| Size | 22.7 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0ccc11afad44a8fe70fdf06c4d4fe98f2b9723fabce3698101e60b9f660af7da
|
|
BLAKE2b-256 checksum How to use checksums |
3fe5f7498d47d70291f6da97265a5045cc7b7a1e9642be6512ec3c6a9db5e450
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.11.7
|
Release files / achatbot-0.0.33.post1-py3-none-any.whl
| Download URL | achatbot-0.0.33.post1-py3-none-any.whl |
|---|---|
| Size | 5.8 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
40c62cf47c31a5673d67452983c7c1d6b4ede41a7f9a4b3096b4373e5a7bac9e
|
|
BLAKE2b-256 checksum How to use checksums |
95c4e2b13a245fae265aacc07524a19db05b3d5ddeedc37a33608b2c0c193a23
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.0.0 CPython/3.11.7
|
