Documentation
¶
Overview ¶
Package provider defines the interface for OCR model providers. Each provider encapsulates the model name, system prompt, and decoder for a specific OCR model (e.g., PaddleOCR-VL, Qwen2.5-VL, etc.).
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Provider ¶
type Provider interface {
// Name returns the provider name (e.g. "paddleocrvl", "qwen3vl").
Name() string
// DefaultModel returns the default model name (e.g. "PaddleOCR-VL-1.6").
DefaultModel() string
// SystemPrompt returns the system prompt for the OCR task.
SystemPrompt() string
// Decoder returns the decoder that parses this model's output format.
Decoder() decoder.Decoder
}
Provider is the interface that OCR model providers must implement.
Directories
¶
| Path | Synopsis |
|---|---|
|
Package paddleocrpy provides OCR via the local PaddleOCR Python library.
|
Package paddleocrpy provides OCR via the local PaddleOCR Python library. |
|
Package paddleocrvl implements the provider.Provider interface for PaddleOCR-VL models, which output text with <|LOC_xxx|> location tokens.
|
Package paddleocrvl implements the provider.Provider interface for PaddleOCR-VL models, which output text with <|LOC_xxx|> location tokens. |
|
qwen
|
|
Click to show internal directories.
Click to hide internal directories.