7b1bb1054f
Large scanned PDFs (hundreds of pages) were slow and fragile end-to-end.
This change addresses the parse, transport, and task-scheduling layers:
docreader (parse + transport):
- Parallelize per-page scanned rendering across processes (forkserver/fork),
with serial fallback. ~4-7x faster on large scanned PDFs; pdfium is not
thread-safe so we fan out across processes. Configurable via
DOCREADER_PDF_RENDER_PARALLELISM.
- Add server-streaming ReadStream RPC: emit one meta frame then one frame per
image, so documents with many page images are no longer capped by the unary
gRPC message-size limit (a 874-page PDF produced ~193MiB of images, far over
the 50MB cap) and memory is bounded on both ends. Unary Read is kept for
backward compatibility; the Go production reader switches to ReadStream.
VLM:
- Make the VLM HTTP timeout configurable (VLM_HTTP_TIMEOUT_SECONDS) and raise
the default 90s -> 180s so dense scanned-page OCR does not time out with
"context deadline exceeded".
Async task queues:
- Isolate high-volume, model-heavy fan-out tasks into dedicated asynq queues so
a single large document cannot saturate the shared worker pool and block
user-facing document parsing:
image:multimodal -> "multimodal"
chunk:extract -> "graph"
question:generation -> "question"
- Register the new queues in the server weight map and the cancel inspector's
scanned-queue set (so cancelling a knowledge still purges its pending tasks).
202 lines
5.0 KiB
Go
202 lines
5.0 KiB
Go
package docparser
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"io"
|
|
"os"
|
|
"strconv"
|
|
"sync"
|
|
"time"
|
|
|
|
docclient "github.com/Tencent/WeKnora/docreader/client"
|
|
"github.com/Tencent/WeKnora/docreader/proto"
|
|
"github.com/Tencent/WeKnora/internal/logger"
|
|
"github.com/Tencent/WeKnora/internal/types"
|
|
"google.golang.org/grpc"
|
|
"google.golang.org/grpc/resolver"
|
|
)
|
|
|
|
func getMaxMessageSize() int {
|
|
if sizeStr := os.Getenv("MAX_FILE_SIZE_MB"); sizeStr != "" {
|
|
if size, err := strconv.Atoi(sizeStr); err == nil && size > 0 {
|
|
return size * 1024 * 1024
|
|
}
|
|
}
|
|
return 50 * 1024 * 1024
|
|
}
|
|
|
|
// GRPCDocumentReader implements DocumentReader over gRPC.
|
|
type GRPCDocumentReader struct {
|
|
mu sync.RWMutex
|
|
conn *grpc.ClientConn
|
|
client proto.DocReaderClient
|
|
addr string
|
|
}
|
|
|
|
func NewGRPCDocumentReader(addr string) (*GRPCDocumentReader, error) {
|
|
p := &GRPCDocumentReader{}
|
|
if addr != "" {
|
|
if err := p.connect(addr); err != nil {
|
|
return nil, err
|
|
}
|
|
}
|
|
return p, nil
|
|
}
|
|
|
|
func (p *GRPCDocumentReader) connect(addr string) error {
|
|
authConfig := docclient.LoadAuthConfigFromEnv()
|
|
opts, err := authConfig.BuildDialOptions(getMaxMessageSize())
|
|
if err != nil {
|
|
return fmt.Errorf("failed to build docreader dial options: %w", err)
|
|
}
|
|
if authConfig.TLSEnabled {
|
|
logger.Infof(context.Background(), "TLS enabled for docreader gRPC client")
|
|
}
|
|
if authConfig.AuthToken != "" {
|
|
logger.Infof(context.Background(),
|
|
"Token authentication enabled for docreader gRPC client (TLS=%v)",
|
|
authConfig.TLSEnabled,
|
|
)
|
|
}
|
|
|
|
resolver.SetDefaultScheme("dns")
|
|
|
|
start := time.Now()
|
|
conn, err := grpc.Dial("dns:///"+addr, opts...)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to connect to docreader: %w", err)
|
|
}
|
|
logger.Infof(context.Background(), "Connected to docreader in %v", time.Since(start))
|
|
|
|
p.conn = conn
|
|
p.client = proto.NewDocReaderClient(conn)
|
|
p.addr = addr
|
|
return nil
|
|
}
|
|
|
|
func (p *GRPCDocumentReader) Reconnect(addr string) error {
|
|
p.mu.Lock()
|
|
defer p.mu.Unlock()
|
|
|
|
if p.conn != nil {
|
|
_ = p.conn.Close()
|
|
p.conn = nil
|
|
p.client = nil
|
|
p.addr = ""
|
|
}
|
|
return p.connect(addr)
|
|
}
|
|
|
|
func (p *GRPCDocumentReader) IsConnected() bool {
|
|
p.mu.RLock()
|
|
defer p.mu.RUnlock()
|
|
return p.conn != nil
|
|
}
|
|
|
|
func (p *GRPCDocumentReader) Close() error {
|
|
p.mu.Lock()
|
|
defer p.mu.Unlock()
|
|
if p.conn != nil {
|
|
return p.conn.Close()
|
|
}
|
|
return nil
|
|
}
|
|
|
|
var errNotConnected = fmt.Errorf("docreader service not connected")
|
|
|
|
func (p *GRPCDocumentReader) Read(ctx context.Context, req *types.ReadRequest) (*types.ReadResult, error) {
|
|
p.mu.RLock()
|
|
client := p.client
|
|
p.mu.RUnlock()
|
|
if client == nil {
|
|
return nil, errNotConnected
|
|
}
|
|
|
|
protoReq := &proto.ReadRequest{
|
|
FileContent: req.FileContent,
|
|
FileName: req.FileName,
|
|
FileType: req.FileType,
|
|
Url: req.URL,
|
|
Title: req.Title,
|
|
RequestId: req.RequestID,
|
|
Config: &proto.ReadConfig{
|
|
ParserEngine: req.ParserEngine,
|
|
ParserEngineOverrides: req.ParserEngineOverrides,
|
|
},
|
|
}
|
|
|
|
// Use the streaming RPC so documents with many page images (large scanned
|
|
// PDFs) are not capped by the unary message-size limit. The meta frame
|
|
// arrives first, followed by one frame per image.
|
|
stream, err := client.ReadStream(ctx, protoReq)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("gRPC ReadStream failed: %w", err)
|
|
}
|
|
|
|
result := &types.ReadResult{}
|
|
gotMeta := false
|
|
for {
|
|
frame, recvErr := stream.Recv()
|
|
if recvErr == io.EOF {
|
|
break
|
|
}
|
|
if recvErr != nil {
|
|
return nil, fmt.Errorf("gRPC ReadStream recv failed: %w", recvErr)
|
|
}
|
|
|
|
if meta := frame.GetMeta(); meta != nil {
|
|
gotMeta = true
|
|
result.MarkdownContent = meta.GetMarkdownContent()
|
|
result.ImageDirPath = meta.GetImageDirPath()
|
|
result.Metadata = meta.GetMetadata()
|
|
result.Error = meta.GetError()
|
|
if n := meta.GetImageCount(); n > 0 {
|
|
result.ImageRefs = make([]types.ImageRef, 0, n)
|
|
}
|
|
continue
|
|
}
|
|
|
|
if img := frame.GetImage(); img != nil {
|
|
result.ImageRefs = append(result.ImageRefs, types.ImageRef{
|
|
Filename: img.GetFilename(),
|
|
OriginalRef: img.GetOriginalRef(),
|
|
MimeType: img.GetMimeType(),
|
|
StorageKey: img.GetStorageKey(),
|
|
ImageData: img.GetImageData(),
|
|
})
|
|
}
|
|
}
|
|
|
|
if !gotMeta {
|
|
return nil, fmt.Errorf("gRPC ReadStream returned no metadata frame")
|
|
}
|
|
return result, nil
|
|
}
|
|
|
|
func (p *GRPCDocumentReader) ListEngines(ctx context.Context, overrides map[string]string) ([]types.ParserEngineInfo, error) {
|
|
p.mu.RLock()
|
|
client := p.client
|
|
p.mu.RUnlock()
|
|
if client == nil {
|
|
return nil, errNotConnected
|
|
}
|
|
|
|
resp, err := client.ListEngines(ctx, &proto.ListEnginesRequest{ConfigOverrides: overrides})
|
|
if err != nil {
|
|
return nil, fmt.Errorf("gRPC ListEngines failed: %w", err)
|
|
}
|
|
|
|
result := make([]types.ParserEngineInfo, 0, len(resp.GetEngines()))
|
|
for _, e := range resp.GetEngines() {
|
|
result = append(result, types.ParserEngineInfo{
|
|
Name: e.GetName(),
|
|
Description: e.GetDescription(),
|
|
FileTypes: e.GetFileTypes(),
|
|
Available: e.GetAvailable(),
|
|
UnavailableReason: e.GetUnavailableReason(),
|
|
})
|
|
}
|
|
return result, nil
|
|
}
|