Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423)

### What problem does this PR solve?

#9869

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>

api/utils/api_utils.py

@@ -705,7 +705,9 @@ TimeoutException = Union[Type[BaseException], BaseException]
 OnTimeoutCallback = Union[Callable[..., Any], Coroutine[Any, Any, Any]]
 
 
-def timeout(seconds: float | int = None, attempts: int = 2, *, exception: Optional[TimeoutException] = None, on_timeout: Optional[OnTimeoutCallback] = None):
+def timeout(seconds: float | int | str = None, attempts: int = 2, *, exception: Optional[TimeoutException] = None, on_timeout: Optional[OnTimeoutCallback] = None):
+    if isinstance(seconds, str):
+        seconds = float(seconds)
     def decorator(func):
         @wraps(func)
         def wrapper(*args, **kwargs):

api/utils/base64_image.py

@@ -1,3 +1,56 @@
 import base64
+import logging
+from functools import partial
+from io import BytesIO
+
+from PIL import Image
+
 test_image_base64 = "iVBORw0KGgoAAAANSUhEUgAAAGQAAABkCAIAAAD/gAIDAAAA6ElEQVR4nO3QwQ3AIBDAsIP9d25XIC+EZE8QZc18w5l9O+AlZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBWYFZgVmBT+IYAHHLHkdEgAAAABJRU5ErkJggg=="
-test_image = base64.b64decode(test_image_base64)
+test_image = base64.b64decode(test_image_base64)
+
+
+async def image2id(d: dict, storage_put_func: partial, objname:str, bucket:str="imagetemps"):
+    import logging
+    from io import BytesIO
+    import trio
+    from rag.svr.task_executor import minio_limiter
+    if not d.get("image"):
+        return
+
+    with BytesIO() as output_buffer:
+        if isinstance(d["image"], bytes):
+            output_buffer.write(d["image"])
+            output_buffer.seek(0)
+        else:
+            # If the image is in RGBA mode, convert it to RGB mode before saving it in JPEG format.
+            if d["image"].mode in ("RGBA", "P"):
+                converted_image = d["image"].convert("RGB")
+                d["image"] = converted_image
+            try:
+                d["image"].save(output_buffer, format='JPEG')
+            except OSError as e:
+                logging.warning(
+                    "Saving image exception, ignore: {}".format(str(e)))
+
+        async with minio_limiter:
+            await trio.to_thread.run_sync(lambda: storage_put_func(bucket=bucket, fnm=objname, binary=output_buffer.getvalue()))
+        d["img_id"] = f"{bucket}-{objname}"
+        if not isinstance(d["image"], bytes):
+            d["image"].close()
+        del d["image"]  # Remove image reference
+
+
+def id2image(image_id:str|None, storage_get_func: partial):
+    if not image_id:
+        return
+    arr = image_id.split("-")
+    if len(arr) != 2:
+        return
+    bkt, nm = image_id.split("-")
+    try:
+        blob = storage_get_func(bucket=bkt, filename=nm)
+        if not blob:
+            return
+        return Image.open(BytesIO(blob))
+    except Exception as e:
+        logging.exception(e)

api/utils/file_utils.py

@@ -155,7 +155,7 @@ def filename_type(filename):
     if re.match(r".*\.pdf$", filename):
         return FileType.PDF.value
 
-    if re.match(r".*\.(eml|doc|docx|ppt|pptx|yml|xml|htm|json|jsonl|ldjson|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html|sql)$", filename):
+    if re.match(r".*\.(msg|eml|doc|docx|ppt|pptx|yml|xml|htm|json|jsonl|ldjson|csv|txt|ini|xls|xlsx|wps|rtf|hlp|pages|numbers|key|md|py|js|java|c|cpp|h|php|go|ts|sh|cs|kt|html|sql)$", filename):
         return FileType.DOC.value
 
     if re.match(r".*\.(wav|flac|ape|alac|wavpack|wv|mp3|aac|ogg|vorbis|opus)$", filename):

api/utils/health.py

@@ -0,0 +1,104 @@
+from timeit import default_timer as timer
+
+from api import settings
+from api.db.db_models import DB
+from rag.utils.redis_conn import REDIS_CONN
+from rag.utils.storage_factory import STORAGE_IMPL
+
+
+def _ok_nok(ok: bool) -> str:
+    return "ok" if ok else "nok"
+
+
+def check_db() -> tuple[bool, dict]:
+    st = timer()
+    try:
+        # lightweight probe; works for MySQL/Postgres
+        DB.execute_sql("SELECT 1")
+        return True, {"elapsed": f"{(timer() - st) * 1000.0:.1f}"}
+    except Exception as e:
+        return False, {"elapsed": f"{(timer() - st) * 1000.0:.1f}", "error": str(e)}
+
+
+def check_redis() -> tuple[bool, dict]:
+    st = timer()
+    try:
+        ok = bool(REDIS_CONN.health())
+        return ok, {"elapsed": f"{(timer() - st) * 1000.0:.1f}"}
+    except Exception as e:
+        return False, {"elapsed": f"{(timer() - st) * 1000.0:.1f}", "error": str(e)}
+
+
+def check_doc_engine() -> tuple[bool, dict]:
+    st = timer()
+    try:
+        meta = settings.docStoreConn.health()
+        # treat any successful call as ok
+        return True, {"elapsed": f"{(timer() - st) * 1000.0:.1f}", **(meta or {})}
+    except Exception as e:
+        return False, {"elapsed": f"{(timer() - st) * 1000.0:.1f}", "error": str(e)}
+
+
+def check_storage() -> tuple[bool, dict]:
+    st = timer()
+    try:
+        STORAGE_IMPL.health()
+        return True, {"elapsed": f"{(timer() - st) * 1000.0:.1f}"}
+    except Exception as e:
+        return False, {"elapsed": f"{(timer() - st) * 1000.0:.1f}", "error": str(e)}
+
+
+def check_chat() -> tuple[bool, dict]:
+    st = timer()
+    try:
+        cfg = getattr(settings, "CHAT_CFG", None)
+        ok = bool(cfg and cfg.get("factory"))
+        return ok, {"elapsed": f"{(timer() - st) * 1000.0:.1f}"}
+    except Exception as e:
+        return False, {"elapsed": f"{(timer() - st) * 1000.0:.1f}", "error": str(e)}
+
+
+def run_health_checks() -> tuple[dict, bool]:
+    result: dict[str, str | dict] = {}
+
+    db_ok, db_meta = check_db()
+    chat_ok, chat_meta = check_chat()
+
+    result["db"] = _ok_nok(db_ok)
+    if not db_ok:
+        result.setdefault("_meta", {})["db"] = db_meta
+
+    result["chat"] = _ok_nok(chat_ok)
+    if not chat_ok:
+        result.setdefault("_meta", {})["chat"] = chat_meta
+
+    # Optional probes (do not change minimal contract but exposed for observability)
+    try:
+        redis_ok, redis_meta = check_redis()
+        result["redis"] = _ok_nok(redis_ok)
+        if not redis_ok:
+            result.setdefault("_meta", {})["redis"] = redis_meta
+    except Exception:
+        result["redis"] = "nok"
+
+    try:
+        doc_ok, doc_meta = check_doc_engine()
+        result["doc_engine"] = _ok_nok(doc_ok)
+        if not doc_ok:
+            result.setdefault("_meta", {})["doc_engine"] = doc_meta
+    except Exception:
+        result["doc_engine"] = "nok"
+
+    try:
+        sto_ok, sto_meta = check_storage()
+        result["storage"] = _ok_nok(sto_ok)
+        if not sto_ok:
+            result.setdefault("_meta", {})["storage"] = sto_meta
+    except Exception:
+        result["storage"] = "nok"
+
+    all_ok = (result.get("db") == "ok") and (result.get("chat") == "ok")
+    result["status"] = "ok" if all_ok else "nok"
+    return result, all_ok
+
+