feat(pipeline): add POST /ingest-raw for direct batch ingestion without LLM
All checks were successful
CI / Lint / Test / Vet (push) Successful in 9s
CI / Mirror to GitHub (push) Has been skipped

Allows callers to provide pre-structured RawPage data directly, bypassing the
LLM extraction step. The pipeline still handles slug computation, frontmatter,
link canonicalization, source back-references, and dedup — only the extraction
is skipped. Useful when a more capable model or manual curation produces the
structured data.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Mathias Bergqvist
2026-04-24 11:15:59 +02:00
parent 3e9a648115
commit 0a70d9e972
6 changed files with 204 additions and 7 deletions

View File

@@ -272,6 +272,48 @@ func (h *Handler) IngestPath(w http.ResponseWriter, r *http.Request) {
writeJSON(w, ingestResponse{Pages: allPages, Warnings: allWarnings})
}
type ingestRawRequest struct {
Source string `json:"source"`
Pages []pipeline.RawPage `json:"pages"`
DryRun bool `json:"dry_run"`
}
// IngestRaw handles POST /ingest-raw — run the pipeline on pre-parsed RawPages,
// skipping the LLM extraction step. Use when the caller has already produced
// structured page data (e.g. from a more capable model or manual curation).
func (h *Handler) IngestRaw(w http.ResponseWriter, r *http.Request) {
var req ingestRawRequest
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
writeError(w, http.StatusBadRequest, "invalid JSON")
return
}
if strings.TrimSpace(req.Source) == "" {
writeError(w, http.StatusBadRequest, "source is required")
return
}
if len(req.Pages) == 0 {
writeError(w, http.StatusBadRequest, "pages is required and must be non-empty")
return
}
result, err := pipeline.RunRaw(h.brainDir, req.Source, req.Pages, req.DryRun)
if err != nil {
h.logger.Error("ingest-raw failed", "source", req.Source, "err", err)
writeError(w, http.StatusInternalServerError, "ingest error")
return
}
pages := result.Pages
if pages == nil {
pages = []string{}
}
warnings := result.Warnings
if warnings == nil {
warnings = []string{}
}
writeJSON(w, ingestResponse{Pages: pages, Warnings: warnings})
}
// BackfillRefs handles POST /backfill-refs — injects source back-references
// into all concept and entity pages based on existing wiki/sources/ pages.
func (h *Handler) BackfillRefs(w http.ResponseWriter, r *http.Request) {

View File

@@ -226,6 +226,85 @@ func TestIngestPath_File(t *testing.T) {
assert.NotEmpty(t, pagesSlice)
}
// ---------------------------------------------------------------------------
// POST /ingest-raw
// ---------------------------------------------------------------------------
func TestIngestRaw_Validation(t *testing.T) {
cases := []struct {
name string
body map[string]any
}{
{"missing source", map[string]any{"pages": []any{map[string]any{"title": "X", "type": "concept", "content": "x"}}}},
{"missing pages", map[string]any{"source": "test-source"}},
{"empty pages", map[string]any{"source": "test-source", "pages": []any{}}},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
_, h := setup(t)
body, _ := json.Marshal(tc.body)
req := httptest.NewRequest(http.MethodPost, "/ingest-raw", bytes.NewReader(body))
rec := httptest.NewRecorder()
h.IngestRaw(rec, req)
assert.Equal(t, http.StatusBadRequest, rec.Code)
})
}
}
func TestIngestRaw_Success(t *testing.T) {
dir, h := setup(t)
body, _ := json.Marshal(map[string]any{
"source": "test-article",
"pages": []any{
map[string]any{"title": "Test Article", "type": "source", "subtype": "article", "domain": "Testing", "content": "## Summary\n\nThis is a test article about [[Test Concept]].\n"},
map[string]any{"title": "Test Concept", "type": "concept", "domain": "Testing", "content": "A concept for testing.\n"},
},
})
req := httptest.NewRequest(http.MethodPost, "/ingest-raw", bytes.NewReader(body))
rec := httptest.NewRecorder()
h.IngestRaw(rec, req)
require.Equal(t, http.StatusOK, rec.Code)
var resp map[string]any
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
pages := resp["pages"].([]any)
assert.Len(t, pages, 2)
// Verify files were written
sourcePath := filepath.Join(dir, "wiki", "sources", "test-article.md")
assert.FileExists(t, sourcePath)
conceptPath := filepath.Join(dir, "wiki", "concepts", "test-concept.md")
assert.FileExists(t, conceptPath)
}
func TestIngestRaw_DryRun(t *testing.T) {
dir, h := setup(t)
body, _ := json.Marshal(map[string]any{
"source": "dry-run-test",
"pages": []any{
map[string]any{"title": "Dry Run Source", "type": "source", "subtype": "article", "content": "Content."},
},
"dry_run": true,
})
req := httptest.NewRequest(http.MethodPost, "/ingest-raw", bytes.NewReader(body))
rec := httptest.NewRecorder()
h.IngestRaw(rec, req)
require.Equal(t, http.StatusOK, rec.Code)
var resp map[string]any
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &resp))
pages := resp["pages"].([]any)
assert.NotEmpty(t, pages)
// Verify no files were written
sourcePath := filepath.Join(dir, "wiki", "sources", "dry-run-test.md")
assert.NoFileExists(t, sourcePath)
}
func TestIngestPath_Directory(t *testing.T) {
_, h := setup(t)