AI Agent與機器人自動化研究

• 區分以下幾個步驟

1. 安裝WSL2，目的在Ubuntu的核心下，使用Linux指令，並可以跑多個Linux虛擬環境
2. 安裝docker desktop，管理多個container
3. 於ubuntu環境安裝Wren AI
4. 使用地端模型設定

wsl -d ubuntu

cd wren-launcher
./wren-launcher-linux

 

Wren AI Demo Site 

GOOD JOB! 完成

 

 以gemma2:2b為例

## LLM
#LLM_PROVIDER=openai_llm # openai_llm, azure_openai_llm, ollama_llm
#GENERATION_MODEL=GPT-4o-mini
#GENERATION_MODEL_KWARGS={"temperature": 0, "n": 1, "max_tokens": 4096, "response_format": {"type": "json_object"}}


LLM_PROVIDER=ollama_llm # openai_llm, azure_openai_llm, ollama_llm
GENERATION_MODEL=gemma2:2b
GENERATION_MODEL_KWARGS={"temperature": 0, "n": 1, "max_tokens": 512, "response_format": {"type": "json_object"}}


# openai or openai-api-compatible
LLM_OPENAI_API_KEY=
LLM_OPENAI_API_BASE=

# azure_openai
LLM_AZURE_OPENAI_API_KEY=
LLM_AZURE_OPENAI_API_BASE=
LLM_AZURE_OPENAI_VERSION=

# ollama
LLM_OLLAMA_URL=http://host.docker.internal:11434


# ## EMBEDDER
# EMBEDDER_PROVIDER=openai_embedder # openai_embedder, azure_openai_embedder, ollama_embedder
# # supported embedding models providers by qdrant: https://qdrant.tech/documentation/embeddings/
# EMBEDDING_MODEL=text-embedding-3-large
# EMBEDDING_MODEL_DIMENSION=3072

## EMBEDDER
EMBEDDER_PROVIDER=ollama_embedder # openai_embedder, azure_openai_embedder, ollama_embedder
# supported embedding models providers by qdrant: https://qdrant.tech/documentation/embeddings/
EMBEDDING_MODEL=nomic-embed-text
EMBEDDING_MODEL_DIMENSION=768 #nomic-embed-text dimension :64~768

# openai or openai-api-compatible
EMBEDDER_OPENAI_API_KEY=
EMBEDDER_OPENAI_API_BASE=

# azure_openai
EMBEDDER_AZURE_OPENAI_API_KEY=
EMBEDDER_AZURE_OPENAI_API_BASE=
EMBEDDER_AZURE_OPENAI_VERSION=

# ollama
EMBEDDER_OLLAMA_URL=http://host.docker.internal:11434


## DOCUMENT_STORE
DOCUMENT_STORE_PROVIDER=qdrant

QDRANT_HOST=qdrant