tkmind/memind
1
0
Fork 0
Code Issues Pull Requests 2 Actions Packages Projects Releases Wiki Activity

feat: configure deep search llm models

Browse Source
This commit is contained in:
john
2026-07-23 22:46:10 +08:00
parent be1e4c18c0
commit 784a10a592
11 changed files with 360 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/deep-search-service.md
+11 -6
View File
@@ -15,7 +15,7 @@ The standalone runtime uses the built-in `node:sqlite` module and therefore requ
7. Generate a Markdown report with numbered citations.
8. Persist task state, sources, events, report, and research memory in SQLite.
The planner and report writer use an OpenAI-compatible model when configured. If the model is unavailable, deterministic planning and citation-safe extractive reporting keep the service operational.
The planner and report writer use an optional model selected from TKMind's Unified Model Center. MindSearch stores only the Provider Key ID and model name. Deep Search calls a secret-protected Portal gateway, and the provider API key never leaves the Portal process. If the selected model is unavailable, deterministic planning and citation-safe extractive reporting keep the service operational.
`createDeepSearchEngine` also accepts an explicit `memorySink` callback. It is disabled by default; an in-process TKMind integration can inject `memoryV2.write` without giving the standalone service an unrestricted outbound memory endpoint. Memory sink failures are fail-open and recorded as task events.
@@ -24,6 +24,7 @@ The planner and report writer use an OpenAI-compatible model when configured. If
```bash
TKMIND_DEEP_SEARCH_SEARXNG_URL=http://127.0.0.1:8080/search \
TKMIND_DEEP_SEARCH_DB=.deep-search/research.sqlite \
TKMIND_DEEP_SEARCH_SECRET=local-shared-secret \
npm run dev:deep-search
```
@@ -70,14 +71,14 @@ Start response:
| `TKMIND_DEEP_SEARCH_DB` | `.deep-search/research.sqlite` | SQLite database |
| `TKMIND_DEEP_SEARCH_SEARXNG_URL` | `http://127.0.0.1:8080/search` | Upstream search endpoint |
| `TKMIND_DEEP_SEARCH_SECRET` | empty | Optional `X-Secret-Key` required by non-health routes |
| `TKMIND_DEEP_SEARCH_LLM_URL` | empty | OpenAI-compatible chat-completions endpoint |
| `TKMIND_DEEP_SEARCH_LLM_API_KEY` | empty | Optional model API key |
| `TKMIND_DEEP_SEARCH_LLM_MODEL` | empty | Planner and report model |
| `TKMIND_DEEP_SEARCH_LLM_GATEWAY_URL` | `http://127.0.0.1:8081/api/internal/deep-search/llm` | Portal LLM gateway |
| `TKMIND_DEEP_SEARCH_LLM_GATEWAY_SECRET` | `TKMIND_DEEP_SEARCH_SECRET` | Portal gateway bearer secret |
## Isolation and safety
- The default bind address is loopback only.
- An optional service secret protects all non-health endpoints.
- The same secret can authenticate the local service to the Portal LLM gateway.
- MCP forwards the current TKMind user ID as `X-User-Id`.
- Task status, event, and cancellation routes enforce user ownership when a user ID is present.
- Source reading rejects credentials, loopback, link-local, private, multicast, and private-DNS destinations.
@@ -94,11 +95,15 @@ The built-in disabled service is:
"adapter": "research-http",
"endpoint": "http://127.0.0.1:20100",
"healthPath": "/health",
"enabled": false
"enabled": false,
"llmProviderKeyId": "",
"llmModel": ""
}
```
After local verification, enable the service and MindSearch in `memindadm`, then select `deep-search` for the `research` route. New Goose sessions receive:
In `memindadm` → `MindSearch` → `TKMind Deep Search`, select an optional active Provider configuration and one of its models. The list comes directly from Unified Model Center. The `测试 LLM` action checks that exact Provider/model combination before saving the MindSearch configuration. Selecting “不使用 LLM（确定性降级）” leaves both fields empty.
After local verification, enable the service and MindSearch, then select `deep-search` for the `research` route. New Goose sessions receive:
- `tkmind_research`
- `tkmind_research_status`