Infrastructure: - docker-compose.yml: replace bifrost container with LiteLLM proxy (host.docker.internal:4000); complex model → deepseek-r1:free via OpenRouter; add Matrix URL env var; mount logs volume - bifrost-config.json: add auth_config + postgres config_store (archived) Routing: - router.py: full semantic 3-tier classifier rewrite — nomic-embed-text centroids for light/medium/complex; regex pre-classifiers for all tiers; Russian utterance sets expanded - agent.py: wire LiteLLM URL; add dry_run support; add Matrix channel Channels: - channels.py: add Matrix adapter (_matrix_send via mx- session prefix) Rules / docs: - agent-pipeline.md: remove /think prefix requirement; document automatic complex tier classification - llm-inference.md: update BIFROST_URL → LITELLM_URL references; add remote model note for complex tier - ARCHITECTURE.md: deleted (superseded by README.md) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
76 lines
1.7 KiB
JSON
76 lines
1.7 KiB
JSON
{
|
|
"auth_config": {
|
|
"is_enabled": true,
|
|
"admin_username": "admin",
|
|
"admin_password": "env.BIFROST_ADMIN_PASSWORD"
|
|
},
|
|
"config_store": {
|
|
"enabled": true,
|
|
"type": "postgres",
|
|
"config": {
|
|
"host": "bifrost-db",
|
|
"port": "5432",
|
|
"user": "bifrost",
|
|
"password": "bifrost",
|
|
"db_name": "bifrost",
|
|
"ssl_mode": "disable"
|
|
}
|
|
},
|
|
"client": {
|
|
"drop_excess_requests": false
|
|
},
|
|
"providers": {
|
|
"ollama": {
|
|
"keys": [
|
|
{
|
|
"name": "ollama-gpu",
|
|
"value": "dummy",
|
|
"models": [
|
|
"qwen2.5:0.5b",
|
|
"qwen2.5:1.5b",
|
|
"qwen3:4b",
|
|
"gemma3:4b",
|
|
"qwen3:8b"
|
|
],
|
|
"weight": 1.0
|
|
}
|
|
],
|
|
"network_config": {
|
|
"base_url": "http://host.docker.internal:11436",
|
|
"default_request_timeout_in_seconds": 300,
|
|
"max_retries": 2,
|
|
"retry_backoff_initial_ms": 500,
|
|
"retry_backoff_max_ms": 10000
|
|
}
|
|
},
|
|
"ollama-cpu": {
|
|
"keys": [
|
|
{
|
|
"name": "ollama-cpu-key",
|
|
"value": "dummy",
|
|
"models": [
|
|
"gemma3:1b",
|
|
"qwen2.5:1.5b",
|
|
"qwen2.5:3b"
|
|
],
|
|
"weight": 1.0
|
|
}
|
|
],
|
|
"network_config": {
|
|
"base_url": "http://host.docker.internal:11435",
|
|
"default_request_timeout_in_seconds": 120,
|
|
"max_retries": 2,
|
|
"retry_backoff_initial_ms": 500,
|
|
"retry_backoff_max_ms": 10000
|
|
},
|
|
"custom_provider_config": {
|
|
"base_provider_type": "openai",
|
|
"allowed_requests": {
|
|
"chat_completion": true,
|
|
"chat_completion_stream": true
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|