Skip to content

feat(query): LLM function-call fallback for structured filter extraction #131

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Copilot wants to merge 6 commits into
base: main
Choose a base branch
from
Open

feat(query): LLM function-call fallback for structured filter extraction #131

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
7935075
Initial plan
Copilot Feb 26, 2026
5fb0727
feat(query): add LLM function-call fallback for structured filter ext…
Copilot Feb 26, 2026
53e39e0
fix(query-filter-parser): cast through unknown to fix TS2352 type error
Copilot Feb 26, 2026
2812e2e
fix(query-filter-parser): address code review comments
Copilot Feb 26, 2026
905fa3c
fix(query-filter-parser): circuit breaker correctness + OpenAI json_s…
Copilot Feb 26, 2026
590fe5f
test(query): add explicit temporal + multi-constraint integration tes…
Copilot Feb 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions .env.example
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,17 @@ ROUTER_LLM_TIMEOUT_MS=2000
# Circuit-breaker cooldown after 5 consecutive failures (default: 30000ms)
ROUTER_LLM_CIRCUIT_BREAK_MS=30000

# --- LLM Filter Extraction (feature-flagged, default off) ---
# When enabled, the API attempts to infer structured FilterDSL conditions from
# natural-language queries when no explicit filter is provided and routing is
# ambiguous (method=default or rule_fallback). All LLM output is validated
# through translateFilter before use; invalid output falls back silently.
ROUTER_FILTER_LLM_ENABLED=false
# Model for filter extraction (default: llama3 for ollama, gpt-4o-mini for openai)
# ROUTER_FILTER_LLM_MODEL=llama3
# Timeout in milliseconds for filter extraction LLM call (default: 1500)
ROUTER_FILTER_LLM_TIMEOUT_MS=1500

# --- Enrichment (optional) ---
ENRICHMENT_ENABLED=false

Expand Down
Loading