ai-agent/cmd/testdata/aiconfig/ai_config.example.yaml

# To use this file, copy it to cmd/testdata/aiconfig/ and rename it to ai_config.yaml.
#
# Configuration guide:
# 1. name: Unique identifier for the configuration. The system uses this field for deduplication and updates.
# 2. provider: Model provider. Always set this to openai because the current AI API calls use the OpenAI-compatible protocol.
# 3. baseUrl: API service endpoint.
# 4. apiKey: API key.
# 5. modelType: Model type. Must be one of the following:
#    - llm: Large language model for chat and reasoning.
#    - embedding: Text embedding model for generating vector representations of text.
#    - rerank: Ranking model for reordering search results.
# 6. modelName: Specific model name, as defined by the provider.
# 7. dimension: Vector dimension.
#    - llm and rerank: Usually set to 0.
#    - embedding: Number of vector dimensions. For example, OpenAI text-embedding-3-small uses 1536.
# 8. maxContextTokens: Maximum context tokens. Use 0 for no limit.
#    - llm and embedding: The maximum number of input tokens supported by the model.
#    - rerank: Usually set to 0.
# 9. maxOutputTokens: Maximum output tokens.
#    - llm: The maximum number of output tokens supported by the model.
#    - embedding and rerank: Usually set to 0.
# 10. timeoutMs: Request timeout in milliseconds.
# 11. maxRetryCount: Number of retry attempts after a failed request.
# 12. rpmLimit: Requests per minute limit. Use 0 for no limit.
# 13. tpmLimit: Tokens per minute limit. Use 0 for no limit.
# 15. sortNo: Sort order for prioritizing models of the same type. Lower numbers have higher priority.
# 16. remark: Notes describing the purpose of this configuration or any special considerations.
#
items:
  - name: LLM
    provider: openai
    baseUrl: https://dashscope.aliyuncs.com/compatible-mode/v1
    apiKey: <REPLACE_WITH_REAL_KEY>
    modelType: llm
    modelName: qwen3.5-plus
    dimension: 0
    maxContextTokens: 128000
    maxOutputTokens: 4096
    timeoutMs: 30000
    maxRetryCount: 1
    rpmLimit: 0
    tpmLimit: 0
    sortNo: 10
    remark: LLM

  - name: embedding
    provider: openai
    baseUrl: https://dashscope.aliyuncs.com/compatible-mode/v1
    apiKey: <REPLACE_WITH_REAL_KEY>
    modelType: embedding
    modelName: qwen3.7-text-embedding
    dimension: 1536
    maxContextTokens: 0
    maxOutputTokens: 0
    timeoutMs: 30000
    maxRetryCount: 1
    rpmLimit: 0
    tpmLimit: 0
    sortNo: 20
    remark: embedding

  - name: rerank
    provider: openai
    baseUrl: https://dashscope.aliyuncs.com/compatible-mode/v1
    apiKey: <REPLACE_WITH_REAL_KEY>
    modelType: rerank
    modelName: qwen3-vl-rerank
    dimension: 0
    maxContextTokens: 0
    maxOutputTokens: 0
    timeoutMs: 30000
    maxRetryCount: 1
    rpmLimit: 0
    tpmLimit: 0
    sortNo: 30
    remark: rerank