66ab93aa37
- ARCHITECTURE.md: comprehensive pipeline description (copied from Gitea wiki) - test_pipeline.py: tests all services, memory, async timing, and recall Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
93 lines
3.2 KiB
Markdown
93 lines
3.2 KiB
Markdown
# Adolf
|
||
|
||
Persistent AI assistant reachable via Telegram. GPU-accelerated inference with long-term memory and web search.
|
||
|
||
## Architecture
|
||
|
||
```
|
||
Telegram user
|
||
↕ (long-polling)
|
||
[grammy] Node.js — port 3001
|
||
- grammY bot polls Telegram
|
||
- on message: fire-and-forget POST /chat to deepagents
|
||
- exposes MCP SSE server: tool send_telegram_message(chat_id, text)
|
||
↕ fire-and-forget HTTP ↕ MCP SSE tool call
|
||
[deepagents] Python FastAPI — port 8000
|
||
- POST /chat → 202 Accepted immediately
|
||
- background task: run LangGraph react agent
|
||
- LLM: qwen3:8b via Ollama GPU (host port 11436)
|
||
- tools: search_memory, get_all_memories, web_search
|
||
- after reply: async fire-and-forget → store memory on CPU
|
||
↕ MCP SSE ↕ HTTP (SearXNG)
|
||
[openmemory] Python + mem0 — port 8765 [SearXNG — port 11437]
|
||
- MCP tools: add_memory, search_memory, get_all_memories
|
||
- mem0 backend: Qdrant (port 6333) + CPU Ollama (port 11435)
|
||
- embedder: nomic-embed-text (768 dims)
|
||
- extractor: gemma3:1b
|
||
- collection: adolf_memories
|
||
```
|
||
|
||
## Queuing and Concurrency
|
||
|
||
Two semaphores prevent resource contention:
|
||
|
||
| Semaphore | Guards | Notes |
|
||
|-----------|--------|-------|
|
||
| `_reply_semaphore(1)` | GPU Ollama (qwen3:8b) | One LLM inference at a time |
|
||
| `_memory_semaphore(1)` | CPU Ollama (gemma3:1b) | One memory store at a time |
|
||
|
||
**Reply-first pipeline:**
|
||
1. User message arrives via Telegram → Grammy forwards to deepagents (fire-and-forget)
|
||
2. Deepagents queues behind `_reply_semaphore`, runs agent, sends reply via Grammy MCP tool
|
||
3. After reply is sent, `asyncio.create_task` fires `store_memory_async` in background
|
||
4. Memory task queues behind `_memory_semaphore`, calls `add_memory` on openmemory
|
||
5. openmemory uses CPU Ollama: embedding (~0.3s) + extraction (~1.6s) → stored in Qdrant
|
||
|
||
Reply latency: ~10–18s (GPU qwen3:8b inference + tool calls).
|
||
Memory latency: ~5–16s (runs async, never blocks replies).
|
||
|
||
## External Services (from openai/ stack)
|
||
|
||
| Service | Host Port | Role |
|
||
|---------|-----------|------|
|
||
| Ollama GPU | 11436 | Main LLM (qwen3:8b) |
|
||
| Ollama CPU | 11435 | Memory embedding + extraction |
|
||
| Qdrant | 6333 | Vector store for memories |
|
||
| SearXNG | 11437 | Web search |
|
||
|
||
## Compose Stack
|
||
|
||
Config: `agap_git/adolf/docker-compose.yml`
|
||
|
||
```bash
|
||
cd agap_git/adolf
|
||
docker compose up -d
|
||
```
|
||
|
||
Requires `TELEGRAM_BOT_TOKEN` in `adolf/.env`.
|
||
|
||
## Memory
|
||
|
||
- Stored per `chat_id` (Telegram user ID) as `user_id` in mem0
|
||
- Semantic search via Qdrant (cosine similarity, 768-dim nomic-embed-text vectors)
|
||
- mem0 uses gemma3:1b to extract structured facts before embedding
|
||
- Collection: `adolf_memories` in Qdrant
|
||
|
||
## Files
|
||
|
||
```
|
||
adolf/
|
||
├── docker-compose.yml Services: deepagents, openmemory, grammy
|
||
├── Dockerfile deepagents container (Python 3.12)
|
||
├── agent.py FastAPI + LangGraph react agent
|
||
├── .env TELEGRAM_BOT_TOKEN (not committed)
|
||
├── openmemory/
|
||
│ ├── server.py FastMCP + mem0 MCP tools
|
||
│ ├── requirements.txt
|
||
│ └── Dockerfile
|
||
└── grammy/
|
||
├── bot.mjs grammY bot + MCP SSE server
|
||
├── package.json
|
||
└── Dockerfile
|
||
```
|