feat(tools): add pdf extraction for minio ingestion

This commit is contained in:
William Valentin
2026-02-16 14:33:58 -08:00
parent 63df791b26
commit e8a785b61f
7 changed files with 105 additions and 20 deletions
+2 -2
View File
@@ -968,7 +968,7 @@ Upload a local file to MinIO and return a temporary presigned download URL.
#### `minio.ingest`
Read a text-like object from MinIO and write it into a memory namespace.
Read a text-like object from MinIO (and PDFs when `pdftotext` is available) and write it into a memory namespace.
```json
{
@@ -1010,7 +1010,7 @@ Read a text-like object from MinIO and write it into a memory namespace.
#### `minio.sync`
Sync text-like objects from a MinIO prefix into nested memory namespaces.
Sync text-like objects from a MinIO prefix into nested memory namespaces (with PDF extraction when available).
```json
{
+16
View File
@@ -141,6 +141,22 @@
],
"test_status": "pnpm test:run src/tools/builtin/k8s.test.ts src/tools/policy.test.ts src/config/schema.test.ts + pnpm typecheck passing"
},
"minio-pdf-ingestion-support": {
"status": "completed",
"date": "2026-02-16",
"updated": "2026-02-16",
"summary": "Extended MinIO knowledge ingestion to support PDF documents via `pdftotext` extraction in both `minio.ingest` and `minio.sync` paths (when available), while preserving text-safety checks for other binary formats. Updated tests and docs accordingly.",
"files_modified": [
"src/tools/builtin/minio-ingest.ts",
"src/tools/builtin/minio-sync.ts",
"src/tools/builtin/minio-ingest.test.ts",
"src/tools/builtin/minio-sync.test.ts",
"README.md",
"docs/api/TOOLS.md",
"docs/plans/state.json"
],
"test_status": "pnpm test:run src/tools/builtin/minio-ingest.test.ts src/tools/builtin/minio-sync.test.ts + pnpm typecheck passing"
},
"backup-session-summary-audit-trail": {
"status": "completed",
"date": "2026-02-16",