Skip to content

fix(#233): improve multi-collection search filtering #241

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
ambicuity wants to merge 2 commits into
base: main
Choose a base branch
from
+126 −92
Open

fix(#233): improve multi-collection search filtering #241

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
82cdf2a
fix(#233): improve multi-collection search filtering at SQL level
ambicuity Feb 21, 2026
db74d50
refactor: apply PR feedback for single IN clause and exit code assertion
ambicuity Feb 21, 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
37 changes: 9 additions & 28 deletions src/qmd.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1298,7 +1298,7 @@ function collectionList(): void {
for (const coll of collections) {
const updatedAt = coll.last_modified ? new Date(coll.last_modified) : new Date();
const timeAgo = formatTimeAgo(updatedAt);

// Get YAML config to check includeByDefault
const yamlColl = getCollectionFromYaml(coll.name);
const excluded = yamlColl?.includeByDefault === false;
Expand Down Expand Up @@ -1998,14 +1998,11 @@ function search(query: string, opts: OutputOptions): void {
// Validate collection filter (supports multiple -c flags)
// Use default collections if none specified
const collectionNames = resolveCollectionFilter(opts.collection, true);
const singleCollection = collectionNames.length === 1 ? collectionNames[0] : undefined;
const effectiveCollections = collectionNames.length > 0 ? collectionNames : undefined;

// Use large limit for --all, otherwise fetch more than needed and let outputResults filter
const fetchLimit = opts.all ? 100000 : Math.max(50, opts.limit * 2);
const results = filterByCollections(
searchFTS(db, query, fetchLimit, singleCollection),
collectionNames
);
const results = searchFTS(db, query, fetchLimit, effectiveCollections);

// Add context to results
const resultsWithContext = results.map(r => ({
Expand Down Expand Up @@ -2053,13 +2050,13 @@ async function vectorSearch(query: string, opts: OutputOptions, _model: string =
// Validate collection filter (supports multiple -c flags)
// Use default collections if none specified
const collectionNames = resolveCollectionFilter(opts.collection, true);
const singleCollection = collectionNames.length === 1 ? collectionNames[0] : undefined;
const effectiveCollections = collectionNames.length > 0 ? collectionNames : undefined;

checkIndexHealth(store.db);

await withLLMSession(async () => {
let results = await vectorSearchQuery(store, query, {
collection: singleCollection,
collection: effectiveCollections,
limit: opts.all ? 500 : (opts.limit || 10),
minScore: opts.minScore || 0.3,
hooks: {
Expand All @@ -2070,14 +2067,6 @@ async function vectorSearch(query: string, opts: OutputOptions, _model: string =
},
});

// Post-filter for multi-collection
if (collectionNames.length > 1) {
results = results.filter(r => {
const prefixes = collectionNames.map(n => `qmd://${n}/`);
return prefixes.some(p => r.file.startsWith(p));
});
}

closeDb();

if (results.length === 0) {
Expand Down Expand Up @@ -2107,7 +2096,7 @@ async function querySearch(query: string, opts: OutputOptions, _embedModel: stri
// Validate collection filter (supports multiple -c flags)
// Use default collections if none specified
const collectionNames = resolveCollectionFilter(opts.collection, true);
const singleCollection = collectionNames.length === 1 ? collectionNames[0] : undefined;
const effectiveCollections = collectionNames.length > 0 ? collectionNames : undefined;

checkIndexHealth(store.db);

Expand All @@ -2121,7 +2110,7 @@ async function querySearch(query: string, opts: OutputOptions, _embedModel: stri
// Structured search — user provided their own query expansions
const typeLabels = structuredQueries.map(s => s.type).join('+');
process.stderr.write(`${c.dim}Structured search: ${structuredQueries.length} queries (${typeLabels})${c.reset}\n`);

// Log each sub-query
for (const s of structuredQueries) {
let preview = s.query.replace(/\n/g, ' ');
Expand All @@ -2131,7 +2120,7 @@ async function querySearch(query: string, opts: OutputOptions, _embedModel: stri
process.stderr.write(`${c.dim}└─ Searching...${c.reset}\n`);

results = await structuredSearch(store, structuredQueries, {
collections: singleCollection ? [singleCollection] : undefined,
collection: effectiveCollections,
limit: opts.all ? 500 : (opts.limit || 10),
minScore: opts.minScore || 0,
hooks: {
Expand All @@ -2154,7 +2143,7 @@ async function querySearch(query: string, opts: OutputOptions, _embedModel: stri
} else {
// Standard hybrid query with automatic expansion
results = await hybridQuery(store, query, {
collection: singleCollection,
collection: effectiveCollections,
limit: opts.all ? 500 : (opts.limit || 10),
minScore: opts.minScore || 0,
hooks: {
Expand Down Expand Up @@ -2187,14 +2176,6 @@ async function querySearch(query: string, opts: OutputOptions, _embedModel: stri
});
}

// Post-filter for multi-collection
if (collectionNames.length > 1) {
results = results.filter(r => {
const prefixes = collectionNames.map(n => `qmd://${n}/`);
return prefixes.some(p => r.file.startsWith(p));
});
}

closeDb();

if (results.length === 0) {
Expand Down
Loading