## Summary
This PR hardens the Go ingestion **Extractor** and **LLM retry** paths
and closes several Python->Go parity gaps in the keyword/question/tag
extraction flow.
- **Generic retry utility** (`internal/common/retry.go`):
`RetryWithBackoff` with exponential backoff (default 3 retries, 2s
initial delay, capped at 1m), context-aware sleep, and a `maxRetries<=0`
fast path. Covered by `internal/common/retry_test.go`.
- **LLM retry reuse**: `agent/component/llm_retry.go` now delegates to
`common.RetryWithBackoff` instead of an inline loop (behavior preserved:
ctx cancellation short-circuits the backoff).
- **Extractor LLM calls** (`extractor.go`):
- `call()` now retries transient LLM failures via `RetryWithBackoff`
(retry exhaustion fails the chunk instead of silently skipping).
- Sets `temperature = 0.2`, matching Python `generator.py:230,245`.
- Runs keyword and question extraction **concurrently** per chunk when
both are enabled (`task_executor.py:444-448`), with mutex-guarded map
writes to avoid data races.
- Substitutes `{field_name}` placeholders (including `{chunks}` -> chunk
text) in `prompt`/`system_prompt` before the call, mirroring Python
`string_format` (`extractor.py:102-103`); unmatched placeholders are
left as-is.
- Falls back to the **tenant default chat model** when `llm_id` is empty
(`task_executor.py:573-574`).
- Strips `` **greedily** (`strings.LastIndex`) in
`cleanExtractionResult`.
- **Auto-tagging** (`extractor_tag.go`): drops the `in.llmID != ""`
guards so an empty `llm_id` no longer skips tagging (uses the tenant
default model), and strips `` greedily in `parseTaggerResponse`.
- **Docs**: fixes a misleading `PresentationChunker` docstring that
claimed per-slide `image`/`position` output (the PPTX path emits none —
unlike PDF), and removes a stale `docs/migration_python_go_diff.md`
reference in `media_dispatch.go`.
## Test plan
- `bash build.sh --test ./internal/common/...` — passes (new retry
utility + tests).
- `bash build.sh --test ./internal/ingestion/component/...` — passes
(extractor/chunker/schema).
- `gofmt` and lefthook pre-commit checks pass.
Note: the personal `docs/migration_python_go_diff.md` working notebook
in the tree is intentionally **not** part of this PR.
---------
Co-authored-by: CodeBuddy <noreply@codebuddy.ai>
## Summary
Aligns the Go ingestion pipeline with the Python implementation, closing
several behavioral gaps found during the Python→Go migration (tracked in
`docs/migration_python_go_diff.md`). Covers parser/media dispatch
alignment, the PDF coordinate-chain (preview images, outline→title,
chunk coordinate finalization), and the Chunker Token/QA batches below.
Commits are grouped as follows.
### 1. Fix parser params (c524f450e)
Fixes parser/media wiring and several dispatch gaps:
- **docx/pdf vision dispatch**: correct parameter handling and VLM
invocation.
- **markdown vision (diff 2.5)**: also enhance items whose
`doc_type_kwd` is `table`, not only `image` (parser/utils.py:181).
- **media audio (diff 2.11)**: when `output_format` is `json`, carry the
ASR transcription as a JSON item instead of only the `Text` field (the
Invoke switch had no `json` branch and dropped it).
- **email (diff 2.2)**: default `output_format` is `json`
(parser.py:212), not `text`.
- **tokenizer**: handle empty/whitespace-only names; trim before
embedding.
- **extractor**: tag-matching parameter wiring.
- **split**: keyword-split regex now covers CJK/English separators.
- **parser.go**: parser-param plumbing.
### 2. fix parser gap (373537da1)
Image dispatch now mirrors `rag/app/picture.py:chunk()`:
- Always OCR the image (PaddleOCR or local ONNX).
- When OCR text is short, also call VLM (`describe`) and combine `OCR +
VLM` text.
- Emits a **structured JSON item** carrying the image data-URI and
`doc_type_kwd:"image"`, instead of a bare `Text` string. This fixes the
payload being rejected downstream by OneChunker/TokenChunker (JSON=nil).
### 3. PDF coordinate-chain fixes (55367a820, 727f8167c)
Closes three items from the migration tracker in the
chunker/tokenizer/task layer:
- **(Chunker-1.3) `restore_pdf_text_previews`** — `needsCrop` now also
returns true for `text` chunks that carry PDF positions
(`pdfcrop_cgo.go`), so text blocks get a rendered preview image uploaded
to storage via `imageUploadDecorator`/`ChunkImageUploader`, matching
Python `restore_pdf_text_previews` + `image2id`.
- **(Chunker-1.5) PDF outline → title levels** — `title.go` adds
`outlineSimilarity` (rune-bigram Jaccard, mirroring
`common.py:_outline_similarity`), `resolveOutlineLevels` (matches text
lines to outline entries at similarity > 0.8, with a sparse guard
`len(outline)/len(records) <= 0.03`), and `outlineFromInputs` (reads
`file.outline`). Wired into `newLevelContext` in both `group.go` and
`hierarchy.go`; falls back to the title-shape heuristic when no outline
is present.
- **(Tokenizer-(T)1) `finalize_pdf_chunk`** — the coordinate →
`position_int`/`page_num_int`/`top_int` conversion is owned by the task
layer (`processChunkPositions`→`AddPositions`), which runs *after* the
tokenizer and consumes the tokenizer-owned fields. The tokenizer only
preserves the raw `positions`/`_pdf_positions` (no duplicate
conversion), pinned by `TestChunkDocsToMaps_PreservesPDFPositions`.
### 4. Integration test made environment-free
(`internal/ingestion/task/pipeline_real_integration_test.go`)
- Removed the `//go:build integration` tag so the contract tests run
under the default `build.sh --test` (which does not pass `-tags
integration`).
- External dependencies replaced with in-memory substitutes so no
MySQL/MinIO/ES is required:
- MySQL → on-disk sqlite (`glebarez/sqlite`) with the needed tables
auto-migrated.
- MinIO → `storage.NewMemoryStorage()`.
- Elasticsearch → chunks captured via `WithInsertFunc` instead of
`engine.InsertChunks`/`Search`.
- `requireTokenizerPool` still skips gracefully when the native
tokenizer pool is unavailable; `WithLogCreateFunc(noop)` avoids
depending on the operation-log table.
- Added `taskChunkFieldEqualsStr` to tolerate `kb_id` being a
`[]string`/`[]any` in the raw chunk payload (the search engine flattens
it to a string on read).
### 5. TokenChunker alignment — Batch 1
(`internal/ingestion/component/chunker/token.go`)
Closes four Chunker items from the migration tracker:
- **(Chunker-2.1) sentence delimiter** — the boundary regex now also
breaks on ASCII `!`/`?`. Extracted to a package-level `var
sentenceDelimiter` and used in `mergeByTokenSize`, matching Python's
full delimiter set.
- **(Chunker-2.2) overlap tag leakage** — when a new chunk starts, its
overlap prefix is taken from the previous chunk *after* `removeTag`, in
both the text path (`mergeByTokenSize`) and the JSON path
(`mergeByTokenSizeFromJSON`). Parser tags (`@@…##`) no longer leak into
the overlap region (mirrors `nlp/__init__.py:1181`).
- **(Chunker-2.11) empty-text merge** — merging a non-empty chunk into
an empty previous chunk now assigns the text directly instead of being
skipped (`mergeByTokenSizeFromJSON`), mirroring
`token_chunker.py:236-239`.
- **(Chunker-2.4) overlap token counting** —
`takeFromEnd`/`takeFromStart` now count tokens exactly via `tokenizeStr`
instead of the 4-bytes/token heuristic, fixing over-counting for CJK
text.
### 6. QA Chunker alignment — Batch 2
(`internal/ingestion/component/chunker/qa.go` + `schema`)
Closes three Chunker items from the migration tracker:
- **(Chunker-2.13) default language** — an empty `lang` now defaults to
Chinese prefixes (`问题：`/`回答：`) instead of English, matching `qa.py:299`.
- **(Chunker-2.12) `rmQAPrefix` regex** — the separator is changed to
`[\t:： ]+` (one-or-more), matching `qa.py:241`, so multiple separators
(e.g. `Q:: answer`) are fully stripped.
- **(Chunker-1.8 QA) missing chunk fields** — QA chunks now preserve:
- `top_int` — the source row/record index, threaded through the
tab/csv/markdown extractors (mirrors `qa.py` `beAdoc(..., row_num=i)`);
- `image` + `doc_type_kwd:"image"`;
- `_pdf_positions` / `positions` carried from the upstream JSON item.
`schema.ChunkDoc` gains a `TopInt []int` field (serialized as `top_int`,
registered in `UnmarshalJSON`). Note: the Tag/Table/Presentation/One
chunker field gaps under 1.8 remain pending.
## Test plan
- Added/updated unit tests: `pdfcrop_cgo_test.go` (`TestNeedsCrop`,
`TestRestorePDFTextPreview`), `title_test.go`
(`TestResolveOutlineLevels`, `TestResolveOutlineLevels_SparseGuard`,
`TestNewLevelContext_OutlineBranch`, `TestOutlineFromInputs`),
`tokenizer_unit_test.go` (`TestChunkDocsToMaps_PreservesPDFPositions`),
`token_pdfpos_test.go`.
- **Batch 1** — `token_batch1_test.go`:
`TestSentenceDelimiterMatchesBangAndQuestion`,
`TestMergeByTokenSizeFromJSON_OverlapStripsTags`,
`TestMergeByTokenSizeFromJSON_EmptyPrevKeepsChunk`,
`TestTakeFromEndRespectsTokenCount`,
`TestTakeFromStartRespectsTokenCount`.
- **Batch 2** — `qa_batch2_test.go`:
`TestQAChunker_DefaultLangIsChinese`,
`TestRmQAPrefixStripsMultipleSeparators`, `TestQAChunker_SetsTopInt`,
`TestQAChunker_CarriesImageAndPositions`. Existing `qa_test.go`
expectations were updated to the corrected language default / separator
behavior.
- `pipeline_real_integration_test.go`
(`TestPipelineExecutor_Run_RealCanvasDSL_UsesGeneralPipeline`,
`TestPipelineExecutor_Run_RealPDF_ProducesIndexedChunks`,
`TestRunPipeline_RealPipelineOutput_ProducesIndexFields`) now runs
without any external service.
- `bash build.sh --test ./internal/ingestion/...` passes.
- No files deleted.
## Summary
This PR aligns the Go ingestion pipeline's **Laws** DSL template with
the Python implementation by fixing heading-detection gaps, adds
image-extension support, refactors the **Extractor** component's LLM
resolution, hardens heading detection for CJK text, and makes the
Extractor accept the Python DSL prompt key names
(`sys_prompt`/`prompts`) alongside the Go names.
## Changes
### 1. Picture file-type detection (`internal/utility/file.go`)
Adds explicit mapping for common image extensions (png, jpg, jpeg, gif,
bmp, tiff, tif, webp, svg, ico, avif, heic, apng) → `FileTypeVISUAL`,
with regression tests.
### 2. Laws DSL heading-detection alignment
(`internal/ingestion/component/chunker/`)
Four fixes to `resolveTitleLevels`:
| Fix | What changed | Why |
|-----|-------------|-----|
| **DOCX `ck_type` fallback** | `ckType` field on `lineRecord`,
propagated from `ChunkDoc.CKType` in `recordsFromStructured`. When
`ck_type=="heading"`, assign `fallbackLevel`. | office_oxide extracts
DOCX heading metadata, but the info was lost before reaching the heading
detector. Word headings whose text doesn't match any regex (e.g.
"Introduction") were treated as body. |
| **`make_colon_as_title` promotion** | `isColonTitle()`: promotes lines
ending with `:`/`：` that have sentence-ending punctuation before the
colon and ≥32 runes between them. | Mirrors Python's
`make_colon_as_title` in `rag/nlp/__init__.py`. Triple guard prevents
false positives. |
| **Short/numeric line filter** | Lines with ≤1 rune or purely numeric
are pinned to body level. | Mirrors Python `tree_merge`'s filter of
`sections` where `len(...) <= 1` or `re.match(r"[0-9]+$", ...)`. |
| **PDF `remove_toc`** | `"remove_toc": true` added to the PDF parser
setup in `ingestion_pipeline_laws.json`. | The Go PDF parser already
supports TOC removal; the Book template already enables it. |
### 3. Extractor llm_id resolution
(`internal/ingestion/component/extractor.go`)
Refactored to handle both **bare tenant_model UUIDs** and **composite
model@provider** strings via the shared `resolveModelConfig`
(`dispatch_model.go`):
- **`resolveExtractorChatConfig`** — UUID path calls
`resolveModelConfigByID` directly (one DB hit); composite path goes
through `resolveModelConfig`. Added `isBareTenantModelID` pre-check for
clear errors when a UUID doesn't exist.
- **`resolveExtractorChatTarget`** — propagates resolution errors
instead of silently returning empty driver.
- **`Chat()`** — removed `driver = "dummy"` fallback. Missing driver is
now an explicit error.
- **Removed dead code**: `splitExtractorLLID`,
`findExtractorSoleActiveInstance`.
### 4. `InjectExtractorLLMID` — fallback when no user config
(`internal/common/parser_config.go`)
Injects the tenant's global default LLM into extractor components **only
when their `llm_id` is empty**. Preserves user-selected UUID or
model@provider values.
Priority: user-configured llm_id > tenant global default > error (no
silent dummy fallback).
### 5. `ResponseHeaderTimeout` increase
(`internal/entity/models/base_model.go`)
`ResponseHeaderTimeout` 60s → 120s in `NewDriverHTTPClient`. Reasoning
models with large extraction prompts can take longer than 60s to produce
the first response token.
### 6. CJK rune-aware heading detection
(`internal/ingestion/component/chunker/title.go`)
Two byte-vs-rune bugs that only manifest on CJK text:
| Fix | What changed | Why |
|-----|-------------|-----|
| **`isColonTitle` byte offset** | `body[lastPunct+1:]` →
`body[lastPunct+runeLen:]` via `utf8.DecodeRuneInString` |
`strings.LastIndexAny` returns a byte index; `+1` skips only 1 byte,
corrupting multi-byte CJK punctuation (e.g. `。` = 3 bytes) and inflating
the rune count past the 32-rune threshold → false-positive heading
promotion. |
| **Short-line filter byte count** | `len(text) <= 1` →
`utf8.RuneCountInString(text) <= 1` | Go `len` is UTF-8 bytes; a single
CJK char (3 bytes) passed the filter, but Python's `len` returns 1 →
mismatch. |
### 7. `extractor_tag.go` — log error when llm fails
When `resolveExtractorChatTarget` returned an error, `runAutoTags` will
log error.
### 8. Python DSL prompt-key compatibility
(`internal/ingestion/component/extractor.go`)
The Resume DSL template uses Python-side key names (`sys_prompt`,
`prompts`). `NewExtractorComponent` now accepts them as fallbacks
alongside the Go names:
- `system_prompt` (Go) ← `sys_prompt` (Python) as fallback
- `prompt` (Go string) ← `prompts` (Python array `[{"role","content"}]`,
takes `[0].content`) as fallback
Mirrors the alias pattern already in `internal/agent/component/llm.go`.
`resolveInputs` accepts per-call `sys_prompt` override too.
## Remaining gaps vs Python
| Gap | Scope | Impact |
|-----|-------|--------|
| **TOC removal for TXT/MD/HTML** | Python's `remove_contents_table`
works on all text formats; Go's `remove_toc` is PDF-only. | Low —
plain-text documents rarely contain structured TOCs. |
| **Regex pattern details** | Minor differences in quantifiers, missing
H5/H6 markdown patterns, missing 4-level numbering pattern. | Low — Go's
variants are stricter; DOCX headings are covered by `ck_type` fallback.
|
## Testing
- `TestHierarchyTitleChunker_CKTypeHeadingFallback` — DOCX `ck_type`
heading promotion
- `TestHierarchyTitleChunker_ColonTitlePromotion` /
`_ColonTitleShortLine_Negative` — colon-title promotion + guard
- `TestIsColonTitle_CJKEdgeCase` / `TestIsColonTitle_ASCII_NoRegression`
— CJK byte-offset fix + ASCII regression
- `TestHierarchyTitleChunker_ColonTitlePromotion_CJK_EdgeCase` — CJK
colon edge case through full pipeline
- `TestHierarchyTitleChunker_ShortSingleCJKLineFilter` — single CJK char
filtered to body
- `TestHierarchyTitleChunker_ShortNumericLineFilter` — purely numeric
lines filtered
- `TestGetFileType_ImageExtensions` / `_ExistingFormats_NoRegression` —
image extension mapping
- `TestInjectExtractorLLMID_SkipWhenUUID` / `_SkipWhenComposite` /
`_InjectWhenEmpty` — llm_id injection guard
- `TestIsBareTenantModelID` — UUID detection
- `TestResolveExtractorChatTarget_AtSplitFallback` / `_NoDriver` — @
split fallback without DB
- `TestNewExtractorComponent_SysPromptAlias` / `_PromptsArray` /
`_PromptsArray_PromptWins` / `_SystemPromptWinsOverSysPrompt` — Python
key compatibility
- `TestBuildDOCXJSONSections_List` / `_TextBox` / `_MixedWithList` —
DOCX list/text_box parsing
- Full ingestion test suite passes (chunker, pipeline, task, service,
component packages)
## Summary
Three groups of changes across the Go ingestion pipeline:
### 1. DOCX parsing improvements
- **docx_parser.go**: Enhanced DOCX parsing with better structure
extraction and media handling
- **docx_parser_cgo_test.go**, **docx_parser_test.go**: Companion tests
- **office_parsers_no_cgo.go**: Stub sync for non-CGO builds
### 2. Email (.eml) parsing: base64 Content-Transfer-Encoding decoding
- **email_parser.go** (`decodeCTE`): Added Content-Transfer-Encoding
decoding for base64 and quoted-printable. Go's `mime/multipart.Reader`
does not decode Content-Transfer-Encoding automatically, so attachments
with `Content-Transfer-Encoding: base64` remained base64-encoded in the
output. The new `decodeCTE` helper is called after reading each
multipart part's raw bytes in `readMailBody`, mirroring Python's
`part.get_payload(decode=True)`.
- **email_parser_test.go**: Two new tests — simple base64 attachment and
nested multipart/alternative with base64 attachment.
### 3. Extractor LLM driver fix + ModelDriver consolidation
- **extractor.go**: Fixed a bug where the Extractor component used
`ModelFactory.CreateModelDriver()`, which creates bare model instances
without API keys or provider configuration. Switched to
`models.GetPreconfiguredDriver()` which resolves the actual
pre-configured driver from `ProviderManager`, matching the codepath used
by `llm.go`. This fixes auto keyword/question extraction in DSL
pipelines that require LLM calls.
- **get_driver.go** (new): Extracted shared `GetPreconfiguredDriver()`
from `llm.go:newChatModelDriver()` so both `llm.go` and `extractor.go`
use the same codepath.
- **get_driver_test.go** (new): Tests for the shared driver resolution.
- **llm.go**: Replaced inline driver resolution with
`models.GetPreconfiguredDriver()`.
### 4. Chunker fixes and observability
- **group.go** (`extractLineRecords`): Fixed to also read `markdown` and
`html` payload keys — previously it only read `text`/`content`, causing
GroupTitleChunker to silently return empty results for markdown-format
parser output.
- **common.go** (`compileDelimPattern`): Aligned with Python's
`_compile_delimiter_pattern` — only backtick-wrapped delimiters produce
an active regex pattern; plain delimiters are not compiled into the
split regex.
- **token.go** (`applyChildrenDelim`): Set `DocType` and `CKType` to
`"text"` on created ChunkDocs so the token-size merge path correctly
identifies and merges text segments.
- **parser.go**, **extractor.go**, **tokenizer.go**, **group.go**,
**hierarchy.go**: Added debug-level logging for pipeline diagnostics.
- **parser_dispatch_test.go**, **group_test.go**: New tests.
## Verification
- All Go tests pass: `bash build.sh --test ./internal/parser/parser/...`
and `bash build.sh --test ./internal/ingestion/component/...`
- Build succeeds: `bash build.sh --go`
Two refactors on the Go port (agent-go-port):
- Remove the dead per-tenant canvas runtime selector (write-only Redis
scaffolding with no runtime callers) and its dependent metrics/admin
code.
- Move the tokenizer embedding-model id from the shared ingestion
globals into a Tokenizer-scoped setup, and wire the production embedder
resolver in the ingestion task package.
32 files changed, 861 insertions, 1228 deletions.
feat(ingestion): mirror Go pipeline progress into the document table;
harden resume guards
- pipeline: bind the owning document via WithDocumentID; after each
TrackProgress event aggregate ingestion_task_log progress and mirror
progress/run/progress_msg back into the document table, so GET
/api/v1/datasets/{dataset_id}/documents reflects live Go pipeline
progress without a bespoke endpoint.
- canvas: extend the S3 resume guard to reject legacy no-op nodes (e.g.
ExitLoop) so component_total equals the count of progress-reporting
components and the aggregate percent can reach 100%.
- runtime/canvas: route progress through TrackProgress; add interrupt
test coverage (r3_interrupt_test.go).
- dao/entity: add IngestionTask.DocumentID column and AggregateProgress
support used by the mirror; IngestionTaskLog keeps a Checkpoint column
alongside the progress fields.
feat(deepdoc): cache DocAnalyzer inference results in Redis (1h TTL)
- Redis-backed DocAnalyzerCache decorator over inference.Client; cache
key = "ddoc:cache:<method>:" + sha256 of the JPEG-encoded image bytes
(deterministic).
- TTL = 1h; hits skip the inner HTTP call and return cached JSON; inner
errors are not cached.
refactor(deepdoc): align figure cropping with Python cropout + bounded
page caches
- CropSectionByDLA mirrors Python cropout: best-overlap DLA
figure/equation region, fallback to section bbox per page, vertical
concat on gray background.
- sliding-window page-image cache bounds peak memory to the recent
window instead of the whole PDF.
- rename DLADebug -> DLARegions across parser/chunker/tests.
refactor(parser): drop lib_type selector; align NewXxxParser with
NewPDFParser
- remove config["lib_type"] lookup and the libType param/field/switch
from all nine constructors; surface the CGO-required error at
ParseWithResult time instead of construction time; drop resolveLibType,
its test, and the four lib_type constants.
feat(utility): add a reusable workerpool for bounded concurrent
execution
- internal/utility/workerpool.go (+ tests).
refactor: translate Chinese prose comments to English in non-harness Go
files.
chore: upgrade github.com/cloudwego/eino from v0.9.9 to v0.9.12.
