Agent Endpoints

Agent endpoints provide AI-powered capabilities including translation, identity analysis, and 5W1H extraction.

POST /api/v1/agents/translate

Translate text between languages using Gemma4 (llama.cpp, port 8082).

Request

{
  "text": "Hello, welcome to Momentry Core.",
  "target_language": "Traditional Chinese",
  "source_language": "English"
}

Response

{
  "success": true,
  "translated_text": "您好，歡迎使用 Momentry Core。",
  "source_language_detected": "English",
  "model_used": "google_gemma-4-26B-A4B-it-Q5_K_M.gguf"
}

Supported Language Pairs (tested)

Model

• Model: Gemma4 26B (Q5_K_M)
• Engine: llama.cpp at localhost:8082
• Endpoint: /v1/chat/completions (OpenAI-compatible)
• Temperature: 0.1
• Max tokens: 1024

Errors

POST /api/v1/agents/5w1h/analyze

Extract 5W1H (Who, What, When, Where, Why, How) from a scene. Uses Gemma4 LLM on port 8082.

Request

{
  "file_uuid": "3abeee81d94597629ed8cb943f182e94",
  "scene_id": 42
}

Response

{
  "success": true,
  "5w1h": {
    "who": ["Cary Grant"],
    "what": ["discussing plans"],
    "when": ["1963"],
    "where": ["Paris"],
    "why": ["vacation"],
    "how": ["in person"]
  }
}

POST /api/v1/agents/5w1h/batch

Batch analyze all scenes in a file for 5W1H extraction. Uses the pipeline's parent_chunk_5w1h.py --mode llm.

Request

{
  "file_uuid": "3abeee81d94597629ed8cb943f182e94"
}

GET /api/v1/agents/5w1h/status

Get status of the 5W1H agent pipeline for a file.

Embedding Model