mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-31 04:07:52 +00:00
fix(gateway): constrain query expansion JSON key to "queries"
The expansion prompt asks the model to "Rewrite the search query below
into 3-4 different, related queries" without naming the JSON key.
On OpenAI-compatible endpoints that don't enforce a strict JSON schema
server-side (e.g. DeepSeek, many self-hosted gateways), the model
picks the prompt-salient noun and emits {"rewrites": [...]}, which
fails ExpansionSchema ({ queries: string[] }) validation. The catch
block only warns for AIConfigError, so the schema-validation failure
silently falls back to [query] and expansion is effectively disabled.
Verified on two providers: oMLX serving Qwen3.6-35B-A3B-6bit at
http://127.0.0.1:8888/v1 and deepseek-v4-flash at
https://api.deepseek.com/v1. With the prompt constraint, both return
{"queries": [...]} and gbrain query latency increases by ~150 ms
(the expansion inference), confirming expansion now runs end-to-end.
Refs #1156
This commit is contained in:
@@ -1624,7 +1624,7 @@ export async function expand(query: string): Promise<string[]> {
|
||||
model,
|
||||
schema: ExpansionSchema,
|
||||
prompt: [
|
||||
'Rewrite the search query below into 3-4 different, related queries that would help find relevant documents.',
|
||||
'Rewrite the search query below into 3-4 different, related queries that would help find relevant documents. Respond with a JSON object in exactly this shape: {"queries": ["rewrite1", "rewrite2", "rewrite3"]}. The JSON key MUST be exactly "queries" (not "rewrites" or any other variation).',
|
||||
'Return ONLY the JSON object. Do NOT include the original query in the result.',
|
||||
'Each rewrite should emphasize different aspects, synonyms, or framings.',
|
||||
'',
|
||||
|
||||
Reference in New Issue
Block a user