Merge pull request #18306 from palazski/main

feat: add mineru as document parser backend with support of both local and managed api

backend/open_webui/config.py

@@ -2297,6 +2297,36 @@ DATALAB_MARKER_OUTPUT_FORMAT = PersistentConfig(
     os.environ.get("DATALAB_MARKER_OUTPUT_FORMAT", "markdown"),
 )
 
+MINERU_API_MODE = PersistentConfig(
+    "MINERU_API_MODE",
+    "rag.mineru_api_mode",
+    os.environ.get("MINERU_API_MODE", "local"),  # "local" or "cloud"
+)
+
+MINERU_API_URL = PersistentConfig(
+    "MINERU_API_URL",
+    "rag.mineru_api_url",
+    os.environ.get("MINERU_API_URL", "http://localhost:8000"),
+)
+
+MINERU_API_KEY = PersistentConfig(
+    "MINERU_API_KEY",
+    "rag.mineru_api_key",
+    os.environ.get("MINERU_API_KEY", ""),
+)
+
+mineru_params = os.getenv("MINERU_PARAMS", "")
+try:
+    mineru_params = json.loads(mineru_params)
+except json.JSONDecodeError:
+    mineru_params = {}
+
+MINERU_PARAMS = PersistentConfig(
+    "MINERU_PARAMS",
+    "rag.mineru_params",
+    mineru_params,
+)
+
 EXTERNAL_DOCUMENT_LOADER_URL = PersistentConfig(
     "EXTERNAL_DOCUMENT_LOADER_URL",
     "rag.external_document_loader_url",

backend/open_webui/main.py

@@ -243,6 +243,10 @@ from open_webui.config import (
     DATALAB_MARKER_DISABLE_IMAGE_EXTRACTION,
     DATALAB_MARKER_FORMAT_LINES,
     DATALAB_MARKER_OUTPUT_FORMAT,
+    MINERU_API_MODE,
+    MINERU_API_URL,
+    MINERU_API_KEY,
+    MINERU_PARAMS,
     DATALAB_MARKER_USE_LLM,
     EXTERNAL_DOCUMENT_LOADER_URL,
     EXTERNAL_DOCUMENT_LOADER_API_KEY,
@@ -853,6 +857,10 @@ app.state.config.DOCLING_PICTURE_DESCRIPTION_API = DOCLING_PICTURE_DESCRIPTION_A
 app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = DOCUMENT_INTELLIGENCE_ENDPOINT
 app.state.config.DOCUMENT_INTELLIGENCE_KEY = DOCUMENT_INTELLIGENCE_KEY
 app.state.config.MISTRAL_OCR_API_KEY = MISTRAL_OCR_API_KEY
+app.state.config.MINERU_API_MODE = MINERU_API_MODE
+app.state.config.MINERU_API_URL = MINERU_API_URL
+app.state.config.MINERU_API_KEY = MINERU_API_KEY
+app.state.config.MINERU_PARAMS = MINERU_PARAMS
 
 app.state.config.TEXT_SPLITTER = RAG_TEXT_SPLITTER
 app.state.config.TIKTOKEN_ENCODING_NAME = TIKTOKEN_ENCODING_NAME

backend/open_webui/retrieval/loaders/main.py

@@ -27,6 +27,7 @@ from open_webui.retrieval.loaders.external_document import ExternalDocumentLoade
 
 from open_webui.retrieval.loaders.mistral import MistralLoader
 from open_webui.retrieval.loaders.datalab_marker import DatalabMarkerLoader
+from open_webui.retrieval.loaders.mineru import MinerULoader
 
 
 from open_webui.env import SRC_LOG_LEVELS, GLOBAL_LOG_LEVEL
@@ -367,6 +368,22 @@ class Loader:
                     api_endpoint=self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT"),
                     azure_credential=DefaultAzureCredential(),
                 )
+        elif self.engine == "mineru" and file_ext in [
+            "pdf",
+            "doc",
+            "docx",
+            "ppt",
+            "pptx",
+            "xls",
+            "xlsx",
+        ]:
+            loader = MinerULoader(
+                file_path=file_path,
+                api_mode=self.kwargs.get("MINERU_API_MODE", "local"),
+                api_url=self.kwargs.get("MINERU_API_URL", "http://localhost:8000"),
+                api_key=self.kwargs.get("MINERU_API_KEY", ""),
+                params=self.kwargs.get("MINERU_PARAMS", {}),
+            )
         elif (
             self.engine == "mistral_ocr"
             and self.kwargs.get("MISTRAL_OCR_API_KEY") != ""

backend/open_webui/retrieval/loaders/mineru.py

@@ -0,0 +1,541 @@
+import os
+import time
+import requests
+import logging
+import tempfile
+import zipfile
+from typing import List, Optional
+from langchain_core.documents import Document
+from fastapi import HTTPException, status
+
+log = logging.getLogger(__name__)
+
+
+class MinerULoader:
+    """
+    MinerU document parser loader supporting both Cloud API and Local API modes.
+
+    Cloud API: Uses MinerU managed service with async task-based processing
+    Local API: Uses self-hosted MinerU API with synchronous processing
+    """
+
+    def __init__(
+        self,
+        file_path: str,
+        api_mode: str = "local",
+        api_url: str = "http://localhost:8000",
+        api_key: str = "",
+        params: dict = None,
+    ):
+        self.file_path = file_path
+        self.api_mode = api_mode.lower()
+        self.api_url = api_url.rstrip("/")
+        self.api_key = api_key
+
+        # Parse params dict with defaults
+        params = params or {}
+        self.enable_ocr = params.get("enable_ocr", False)
+        self.enable_formula = params.get("enable_formula", True)
+        self.enable_table = params.get("enable_table", True)
+        self.language = params.get("language", "en")
+        self.model_version = params.get("model_version", "pipeline")
+        self.page_ranges = params.get("page_ranges", "")
+
+        # Validate API mode
+        if self.api_mode not in ["local", "cloud"]:
+            raise ValueError(
+                f"Invalid API mode: {self.api_mode}. Must be 'local' or 'cloud'"
+            )
+
+        # Validate Cloud API requirements
+        if self.api_mode == "cloud" and not self.api_key:
+            raise ValueError("API key is required for Cloud API mode")
+
+    def load(self) -> List[Document]:
+        """
+        Main entry point for loading and parsing the document.
+        Routes to Cloud or Local API based on api_mode.
+        """
+        try:
+            if self.api_mode == "cloud":
+                return self._load_cloud_api()
+            else:
+                return self._load_local_api()
+        except Exception as e:
+            log.error(f"Error loading document with MinerU: {e}")
+            raise
+
+    def _load_local_api(self) -> List[Document]:
+        """
+        Load document using Local API (synchronous).
+        Posts file to /file_parse endpoint and gets immediate response.
+        """
+        log.info(f"Using MinerU Local API at {self.api_url}")
+
+        filename = os.path.basename(self.file_path)
+
+        # Build form data for Local API
+        form_data = {
+            "return_md": "true",
+            "formula_enable": str(self.enable_formula).lower(),
+            "table_enable": str(self.enable_table).lower(),
+        }
+
+        # Parse method based on OCR setting
+        if self.enable_ocr:
+            form_data["parse_method"] = "ocr"
+        else:
+            form_data["parse_method"] = "auto"
+
+        # Language configuration (Local API uses lang_list array)
+        if self.language:
+            form_data["lang_list"] = self.language
+
+        # Backend/model version (Local API uses "backend" parameter)
+        if self.model_version == "vlm":
+            form_data["backend"] = "vlm-vllm-engine"
+        else:
+            form_data["backend"] = "pipeline"
+
+        # Page ranges (Local API uses start_page_id and end_page_id)
+        if self.page_ranges:
+            # For simplicity, if page_ranges is specified, log a warning
+            # Full page range parsing would require parsing the string
+            log.warning(
+                f"Page ranges '{self.page_ranges}' specified but Local API uses different format. "
+                "Consider using start_page_id/end_page_id parameters if needed."
+            )
+
+        try:
+            with open(self.file_path, "rb") as f:
+                files = {"files": (filename, f, "application/octet-stream")}
+
+                log.info(f"Sending file to MinerU Local API: {filename}")
+                log.debug(f"Local API parameters: {form_data}")
+
+                response = requests.post(
+                    f"{self.api_url}/file_parse",
+                    data=form_data,
+                    files=files,
+                    timeout=300,  # 5 minute timeout for large documents
+                )
+                response.raise_for_status()
+
+        except FileNotFoundError:
+            raise HTTPException(
+                status.HTTP_404_NOT_FOUND, detail=f"File not found: {self.file_path}"
+            )
+        except requests.Timeout:
+            raise HTTPException(
+                status.HTTP_504_GATEWAY_TIMEOUT,
+                detail="MinerU Local API request timed out",
+            )
+        except requests.HTTPError as e:
+            error_detail = f"MinerU Local API request failed: {e}"
+            if e.response is not None:
+                try:
+                    error_data = e.response.json()
+                    error_detail += f" - {error_data}"
+                except:
+                    error_detail += f" - {e.response.text}"
+            raise HTTPException(status.HTTP_400_BAD_REQUEST, detail=error_detail)
+        except Exception as e:
+            raise HTTPException(
+                status.HTTP_500_INTERNAL_SERVER_ERROR,
+                detail=f"Error calling MinerU Local API: {str(e)}",
+            )
+
+        # Parse response
+        try:
+            result = response.json()
+        except ValueError as e:
+            raise HTTPException(
+                status.HTTP_502_BAD_GATEWAY,
+                detail=f"Invalid JSON response from MinerU Local API: {e}",
+            )
+
+        # Extract markdown content from response
+        if "results" not in result:
+            raise HTTPException(
+                status.HTTP_502_BAD_GATEWAY,
+                detail="MinerU Local API response missing 'results' field",
+            )
+
+        results = result["results"]
+        if not results:
+            raise HTTPException(
+                status.HTTP_400_BAD_REQUEST,
+                detail="MinerU returned empty results",
+            )
+
+        # Get the first (and typically only) result
+        file_result = list(results.values())[0]
+        markdown_content = file_result.get("md_content", "")
+
+        if not markdown_content:
+            raise HTTPException(
+                status.HTTP_400_BAD_REQUEST,
+                detail="MinerU returned empty markdown content",
+            )
+
+        log.info(f"Successfully parsed document with MinerU Local API: {filename}")
+
+        # Create metadata
+        metadata = {
+            "source": filename,
+            "api_mode": "local",
+            "backend": result.get("backend", "unknown"),
+            "version": result.get("version", "unknown"),
+        }
+
+        return [Document(page_content=markdown_content, metadata=metadata)]
+
+    def _load_cloud_api(self) -> List[Document]:
+        """
+        Load document using Cloud API (asynchronous).
+        Uses batch upload endpoint to avoid need for public file URLs.
+        """
+        log.info(f"Using MinerU Cloud API at {self.api_url}")
+
+        filename = os.path.basename(self.file_path)
+
+        # Step 1: Request presigned upload URL
+        batch_id, upload_url = self._request_upload_url(filename)
+
+        # Step 2: Upload file to presigned URL
+        self._upload_to_presigned_url(upload_url)
+
+        # Step 3: Poll for results
+        result = self._poll_batch_status(batch_id, filename)
+
+        # Step 4: Download and extract markdown from ZIP
+        markdown_content = self._download_and_extract_zip(
+            result["full_zip_url"], filename
+        )
+
+        log.info(f"Successfully parsed document with MinerU Cloud API: {filename}")
+
+        # Create metadata
+        metadata = {
+            "source": filename,
+            "api_mode": "cloud",
+            "batch_id": batch_id,
+        }
+
+        return [Document(page_content=markdown_content, metadata=metadata)]
+
+    def _request_upload_url(self, filename: str) -> tuple:
+        """
+        Request presigned upload URL from Cloud API.
+        Returns (batch_id, upload_url).
+        """
+        headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json",
+        }
+
+        # Build request body
+        request_body = {
+            "enable_formula": self.enable_formula,
+            "enable_table": self.enable_table,
+            "language": self.language,
+            "model_version": self.model_version,
+            "files": [
+                {
+                    "name": filename,
+                    "is_ocr": self.enable_ocr,
+                }
+            ],
+        }
+
+        # Add page ranges if specified
+        if self.page_ranges:
+            request_body["files"][0]["page_ranges"] = self.page_ranges
+
+        log.info(f"Requesting upload URL for: {filename}")
+        log.debug(f"Cloud API request body: {request_body}")
+
+        try:
+            response = requests.post(
+                f"{self.api_url}/file-urls/batch",
+                headers=headers,
+                json=request_body,
+                timeout=30,
+            )
+            response.raise_for_status()
+        except requests.HTTPError as e:
+            error_detail = f"Failed to request upload URL: {e}"
+            if e.response is not None:
+                try:
+                    error_data = e.response.json()
+                    error_detail += f" - {error_data.get('msg', error_data)}"
+                except:
+                    error_detail += f" - {e.response.text}"
+            raise HTTPException(status.HTTP_400_BAD_REQUEST, detail=error_detail)
+        except Exception as e:
+            raise HTTPException(
+                status.HTTP_500_INTERNAL_SERVER_ERROR,
+                detail=f"Error requesting upload URL: {str(e)}",
+            )
+
+        try:
+            result = response.json()
+        except ValueError as e:
+            raise HTTPException(
+                status.HTTP_502_BAD_GATEWAY,
+                detail=f"Invalid JSON response: {e}",
+            )
+
+        # Check for API error response
+        if result.get("code") != 0:
+            raise HTTPException(
+                status.HTTP_400_BAD_REQUEST,
+                detail=f"MinerU Cloud API error: {result.get('msg', 'Unknown error')}",
+            )
+
+        data = result.get("data", {})
+        batch_id = data.get("batch_id")
+        file_urls = data.get("file_urls", [])
+
+        if not batch_id or not file_urls:
+            raise HTTPException(
+                status.HTTP_502_BAD_GATEWAY,
+                detail="MinerU Cloud API response missing batch_id or file_urls",
+            )
+
+        upload_url = file_urls[0]
+        log.info(f"Received upload URL for batch: {batch_id}")
+
+        return batch_id, upload_url
+
+    def _upload_to_presigned_url(self, upload_url: str) -> None:
+        """
+        Upload file to presigned URL (no authentication needed).
+        """
+        log.info(f"Uploading file to presigned URL")
+
+        try:
+            with open(self.file_path, "rb") as f:
+                response = requests.put(
+                    upload_url,
+                    data=f,
+                    timeout=300,  # 5 minute timeout for large files
+                )
+                response.raise_for_status()
+        except FileNotFoundError:
+            raise HTTPException(
+                status.HTTP_404_NOT_FOUND, detail=f"File not found: {self.file_path}"
+            )
+        except requests.Timeout:
+            raise HTTPException(
+                status.HTTP_504_GATEWAY_TIMEOUT,
+                detail="File upload to presigned URL timed out",
+            )
+        except requests.HTTPError as e:
+            raise HTTPException(
+                status.HTTP_400_BAD_REQUEST,
+                detail=f"Failed to upload file to presigned URL: {e}",
+            )
+        except Exception as e:
+            raise HTTPException(
+                status.HTTP_500_INTERNAL_SERVER_ERROR,
+                detail=f"Error uploading file: {str(e)}",
+            )
+
+        log.info("File uploaded successfully")
+
+    def _poll_batch_status(self, batch_id: str, filename: str) -> dict:
+        """
+        Poll batch status until completion.
+        Returns the result dict for the file.
+        """
+        headers = {
+            "Authorization": f"Bearer {self.api_key}",
+        }
+
+        max_iterations = 300  # 10 minutes max (2 seconds per iteration)
+        poll_interval = 2  # seconds
+
+        log.info(f"Polling batch status: {batch_id}")
+
+        for iteration in range(max_iterations):
+            try:
+                response = requests.get(
+                    f"{self.api_url}/extract-results/batch/{batch_id}",
+                    headers=headers,
+                    timeout=30,
+                )
+                response.raise_for_status()
+            except requests.HTTPError as e:
+                error_detail = f"Failed to poll batch status: {e}"
+                if e.response is not None:
+                    try:
+                        error_data = e.response.json()
+                        error_detail += f" - {error_data.get('msg', error_data)}"
+                    except:
+                        error_detail += f" - {e.response.text}"
+                raise HTTPException(status.HTTP_400_BAD_REQUEST, detail=error_detail)
+            except Exception as e:
+                raise HTTPException(
+                    status.HTTP_500_INTERNAL_SERVER_ERROR,
+                    detail=f"Error polling batch status: {str(e)}",
+                )
+
+            try:
+                result = response.json()
+            except ValueError as e:
+                raise HTTPException(
+                    status.HTTP_502_BAD_GATEWAY,
+                    detail=f"Invalid JSON response while polling: {e}",
+                )
+
+            # Check for API error response
+            if result.get("code") != 0:
+                raise HTTPException(
+                    status.HTTP_400_BAD_REQUEST,
+                    detail=f"MinerU Cloud API error: {result.get('msg', 'Unknown error')}",
+                )
+
+            data = result.get("data", {})
+            extract_result = data.get("extract_result", [])
+
+            # Find our file in the batch results
+            file_result = None
+            for item in extract_result:
+                if item.get("file_name") == filename:
+                    file_result = item
+                    break
+
+            if not file_result:
+                raise HTTPException(
+                    status.HTTP_502_BAD_GATEWAY,
+                    detail=f"File {filename} not found in batch results",
+                )
+
+            state = file_result.get("state")
+
+            if state == "done":
+                log.info(f"Processing complete for {filename}")
+                return file_result
+            elif state == "failed":
+                error_msg = file_result.get("err_msg", "Unknown error")
+                raise HTTPException(
+                    status.HTTP_400_BAD_REQUEST,
+                    detail=f"MinerU processing failed: {error_msg}",
+                )
+            elif state in ["waiting-file", "pending", "running", "converting"]:
+                # Still processing
+                if iteration % 10 == 0:  # Log every 20 seconds
+                    log.info(
+                        f"Processing status: {state} (iteration {iteration + 1}/{max_iterations})"
+                    )
+                time.sleep(poll_interval)
+            else:
+                log.warning(f"Unknown state: {state}")
+                time.sleep(poll_interval)
+
+        # Timeout
+        raise HTTPException(
+            status.HTTP_504_GATEWAY_TIMEOUT,
+            detail="MinerU processing timed out after 10 minutes",
+        )
+
+    def _download_and_extract_zip(self, zip_url: str, filename: str) -> str:
+        """
+        Download ZIP file from CDN and extract markdown content.
+        Returns the markdown content as a string.
+        """
+        log.info(f"Downloading results from: {zip_url}")
+
+        try:
+            response = requests.get(zip_url, timeout=60)
+            response.raise_for_status()
+        except requests.HTTPError as e:
+            raise HTTPException(
+                status.HTTP_400_BAD_REQUEST,
+                detail=f"Failed to download results ZIP: {e}",
+            )
+        except Exception as e:
+            raise HTTPException(
+                status.HTTP_500_INTERNAL_SERVER_ERROR,
+                detail=f"Error downloading results: {str(e)}",
+            )
+
+        # Save ZIP to temporary file and extract
+        try:
+            with tempfile.NamedTemporaryFile(delete=False, suffix=".zip") as tmp_zip:
+                tmp_zip.write(response.content)
+                tmp_zip_path = tmp_zip.name
+
+            with tempfile.TemporaryDirectory() as tmp_dir:
+                # Extract ZIP
+                with zipfile.ZipFile(tmp_zip_path, "r") as zip_ref:
+                    zip_ref.extractall(tmp_dir)
+
+                # Find markdown file - search recursively for any .md file
+                markdown_content = None
+                found_md_path = None
+
+                # First, list all files in the ZIP for debugging
+                all_files = []
+                for root, dirs, files in os.walk(tmp_dir):
+                    for file in files:
+                        full_path = os.path.join(root, file)
+                        all_files.append(full_path)
+                        # Look for any .md file
+                        if file.endswith(".md"):
+                            found_md_path = full_path
+                            log.info(f"Found markdown file at: {full_path}")
+                            try:
+                                with open(full_path, "r", encoding="utf-8") as f:
+                                    markdown_content = f.read()
+                                if (
+                                    markdown_content
+                                ):  # Use the first non-empty markdown file
+                                    break
+                            except Exception as e:
+                                log.warning(f"Failed to read {full_path}: {e}")
+                    if markdown_content:
+                        break
+
+                if markdown_content is None:
+                    log.error(f"Available files in ZIP: {all_files}")
+                    # Try to provide more helpful error message
+                    md_files = [f for f in all_files if f.endswith(".md")]
+                    if md_files:
+                        error_msg = (
+                            f"Found .md files but couldn't read them: {md_files}"
+                        )
+                    else:
+                        error_msg = (
+                            f"No .md files found in ZIP. Available files: {all_files}"
+                        )
+                    raise HTTPException(
+                        status.HTTP_502_BAD_GATEWAY,
+                        detail=error_msg,
+                    )
+
+            # Clean up temporary ZIP file
+            os.unlink(tmp_zip_path)
+
+        except zipfile.BadZipFile as e:
+            raise HTTPException(
+                status.HTTP_502_BAD_GATEWAY,
+                detail=f"Invalid ZIP file received: {e}",
+            )
+        except Exception as e:
+            raise HTTPException(
+                status.HTTP_500_INTERNAL_SERVER_ERROR,
+                detail=f"Error extracting ZIP: {str(e)}",
+            )
+
+        if not markdown_content:
+            raise HTTPException(
+                status.HTTP_400_BAD_REQUEST,
+                detail="Extracted markdown content is empty",
+            )
+
+        log.info(
+            f"Successfully extracted markdown content ({len(markdown_content)} characters)"
+        )
+        return markdown_content

backend/open_webui/routers/retrieval.py

@@ -466,6 +466,11 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
         "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
         "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY,
+        # MinerU settings
+        "MINERU_API_MODE": request.app.state.config.MINERU_API_MODE,
+        "MINERU_API_URL": request.app.state.config.MINERU_API_URL,
+        "MINERU_API_KEY": request.app.state.config.MINERU_API_KEY,
+        "MINERU_PARAMS": request.app.state.config.MINERU_PARAMS,
         # Reranking settings
         "RAG_RERANKING_MODEL": request.app.state.config.RAG_RERANKING_MODEL,
         "RAG_RERANKING_ENGINE": request.app.state.config.RAG_RERANKING_ENGINE,
@@ -647,6 +652,12 @@ class ConfigForm(BaseModel):
     DOCUMENT_INTELLIGENCE_KEY: Optional[str] = None
     MISTRAL_OCR_API_KEY: Optional[str] = None
 
+    # MinerU settings
+    MINERU_API_MODE: Optional[str] = None
+    MINERU_API_URL: Optional[str] = None
+    MINERU_API_KEY: Optional[str] = None
+    MINERU_PARAMS: Optional[dict] = None
+
     # Reranking settings
     RAG_RERANKING_MODEL: Optional[str] = None
     RAG_RERANKING_ENGINE: Optional[str] = None
@@ -886,6 +897,28 @@ async def update_rag_config(
         else request.app.state.config.MISTRAL_OCR_API_KEY
     )
 
+    # MinerU settings
+    request.app.state.config.MINERU_API_MODE = (
+        form_data.MINERU_API_MODE
+        if form_data.MINERU_API_MODE is not None
+        else request.app.state.config.MINERU_API_MODE
+    )
+    request.app.state.config.MINERU_API_URL = (
+        form_data.MINERU_API_URL
+        if form_data.MINERU_API_URL is not None
+        else request.app.state.config.MINERU_API_URL
+    )
+    request.app.state.config.MINERU_API_KEY = (
+        form_data.MINERU_API_KEY
+        if form_data.MINERU_API_KEY is not None
+        else request.app.state.config.MINERU_API_KEY
+    )
+    request.app.state.config.MINERU_PARAMS = (
+        form_data.MINERU_PARAMS
+        if form_data.MINERU_PARAMS is not None
+        else request.app.state.config.MINERU_PARAMS
+    )
+
     # Reranking settings
     if request.app.state.config.RAG_RERANKING_ENGINE == "":
         # Unloading the internal reranker and clear VRAM memory
@@ -1150,6 +1183,11 @@ async def update_rag_config(
         "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
         "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
         "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY,
+        # MinerU settings
+        "MINERU_API_MODE": request.app.state.config.MINERU_API_MODE,
+        "MINERU_API_URL": request.app.state.config.MINERU_API_URL,
+        "MINERU_API_KEY": request.app.state.config.MINERU_API_KEY,
+        "MINERU_PARAMS": request.app.state.config.MINERU_PARAMS,
         # Reranking settings
         "RAG_RERANKING_MODEL": request.app.state.config.RAG_RERANKING_MODEL,
         "RAG_RERANKING_ENGINE": request.app.state.config.RAG_RERANKING_ENGINE,
@@ -1560,6 +1598,10 @@ def process_file(
                         DOCUMENT_INTELLIGENCE_ENDPOINT=request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
                         DOCUMENT_INTELLIGENCE_KEY=request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
                         MISTRAL_OCR_API_KEY=request.app.state.config.MISTRAL_OCR_API_KEY,
+                        MINERU_API_MODE=request.app.state.config.MINERU_API_MODE,
+                        MINERU_API_URL=request.app.state.config.MINERU_API_URL,
+                        MINERU_API_KEY=request.app.state.config.MINERU_API_KEY,
+                        MINERU_PARAMS=request.app.state.config.MINERU_PARAMS,
                     )
                     docs = loader.load(
                         file.filename, file.meta.get("content_type"), file_path

src/lib/components/admin/Settings/Documents.svelte

@@ -207,6 +207,15 @@
 			return;
 		}
 
+		if (
+			RAGConfig.CONTENT_EXTRACTION_ENGINE === 'mineru' &&
+			RAGConfig.MINERU_API_MODE === 'cloud' &&
+			RAGConfig.MINERU_API_KEY === ''
+		) {
+			toast.error($i18n.t('MinerU API Key required for Cloud API mode.'));
+			return;
+		}
+
 		if (!RAGConfig.BYPASS_EMBEDDING_AND_RETRIEVAL) {
 			await embeddingModelUpdateHandler();
 		}
@@ -337,6 +346,7 @@
 									<option value="datalab_marker">{$i18n.t('Datalab Marker API')}</option>
 									<option value="document_intelligence">{$i18n.t('Document Intelligence')}</option>
 									<option value="mistral_ocr">{$i18n.t('Mistral OCR')}</option>
+									<option value="mineru">{$i18n.t('MinerU')}</option>
 								</select>
 							</div>
 						</div>
@@ -749,6 +759,88 @@
 									bind:value={RAGConfig.MISTRAL_OCR_API_KEY}
 								/>
 							</div>
+					{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'mineru'}
+						<!-- API Mode Selection -->
+						<div class="flex w-full mt-2">
+							<div class="flex-1 flex justify-between">
+								<div class="self-center text-xs font-medium">
+									{$i18n.t('API Mode')}
+								</div>
+								<select
+									class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 text-xs bg-transparent outline-hidden"
+									bind:value={RAGConfig.MINERU_API_MODE}
+									on:change={() => {
+										// Auto-update URL when switching modes if it's empty or matches the opposite mode's default
+										const cloudUrl = 'https://mineru.net/api/v4';
+										const localUrl = 'http://localhost:8000';
+										
+										if (RAGConfig.MINERU_API_MODE === 'cloud') {
+											if (!RAGConfig.MINERU_API_URL || RAGConfig.MINERU_API_URL === localUrl) {
+												RAGConfig.MINERU_API_URL = cloudUrl;
+											}
+										} else {
+											if (!RAGConfig.MINERU_API_URL || RAGConfig.MINERU_API_URL === cloudUrl) {
+												RAGConfig.MINERU_API_URL = localUrl;
+											}
+										}
+									}}
+								>
+									<option value="local">{$i18n.t('Self-Hosted')}</option>
+									<option value="cloud">{$i18n.t('minerU managed (Cloud API)')}</option>
+								</select>
+							</div>
+						</div>
+
+						<!-- API URL -->
+						<div class="flex w-full mt-2">
+							<input
+								class="flex-1 w-full text-sm bg-transparent outline-hidden"
+								placeholder={RAGConfig.MINERU_API_MODE === 'cloud' 
+									? $i18n.t('https://mineru.net/api/v4')
+									: $i18n.t('http://localhost:8000')}
+								bind:value={RAGConfig.MINERU_API_URL}
+							/>
+						</div>
+
+						<!-- API Key (Cloud only) -->
+						{#if RAGConfig.MINERU_API_MODE === 'cloud'}
+							<div class="flex w-full mt-2">
+								<SensitiveInput
+									placeholder={$i18n.t('Enter MinerU API Key')}
+									bind:value={RAGConfig.MINERU_API_KEY}
+								/>
+							</div>
+						{/if}
+
+						<!-- Parameters -->
+						<div class="flex justify-between w-full mt-2">
+							<div class="self-center text-xs font-medium">
+								<Tooltip 
+									content={$i18n.t('Advanced parameters for MinerU parsing (enable_ocr, enable_formula, enable_table, language, model_version, page_ranges)')} 
+									placement="top-start"
+								>
+									{$i18n.t('Parameters')}
+								</Tooltip>
+							</div>
+							<div class="">
+								<Textarea
+									value={typeof RAGConfig.MINERU_PARAMS === 'object' && RAGConfig.MINERU_PARAMS !== null && Object.keys(RAGConfig.MINERU_PARAMS).length > 0
+										? JSON.stringify(RAGConfig.MINERU_PARAMS, null, 2)
+										: ''}
+									on:input={(e) => {
+										try {
+											const value = e.target.value.trim();
+											RAGConfig.MINERU_PARAMS = value ? JSON.parse(value) : {};
+										} catch (err) {
+											// Keep the string value if JSON is invalid (user is still typing)
+											RAGConfig.MINERU_PARAMS = e.target.value;
+										}
+									}}
+									placeholder={`{\n  "enable_ocr": false,\n  "enable_formula": true,\n  "enable_table": true,\n  "language": "en",\n  "model_version": "pipeline",\n  "page_ranges": ""\n}`}
+									minSize={100}
+								/>
+							</div>
+						</div>
 					{/if}
 					</div>