Commit fcb5660f authored by myhloli's avatar myhloli
Browse files

feat: add support for JPEG images and update documentation

- Add '.jpeg' to the list of supported image extensions in app.py and read_api.py
- Update projects READMEs to indicate that web_demo is deprecated
parent d105d87c
......@@ -116,7 +116,7 @@ def read_local_office(path: str) -> list[PymuDocDataset]:
shutil.rmtree(temp_dir)
return ret
def read_local_images(path: str, suffixes: list[str]=['.png', '.jpg']) -> list[ImageDataset]:
def read_local_images(path: str, suffixes: list[str]=['.png', '.jpg', '.jpeg']) -> list[ImageDataset]:
"""Read images from path or directory.
Args:
......
......@@ -4,6 +4,6 @@
- [llama_index_rag](./llama_index_rag/README.md): Build a lightweight RAG system based on llama_index
- [gradio_app](./gradio_app/README.md): Build a web app based on gradio
- [web_demo](./web_demo/README.md): MinerU online [demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/) localized deployment version
- ~~[web_demo](./web_demo/README.md): MinerU online [demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/) localized deployment version~~(Deprecated)
- [web_api](./web_api/README.md): Web API Based on FastAPI
- [multi_gpu](./multi_gpu/README.md): Multi-GPU parallel processing based on LitServe
......@@ -4,6 +4,6 @@
- [llama_index_rag](./llama_index_rag/README_zh-CN.md): 基于 llama_index 构建轻量级 RAG 系统
- [gradio_app](./gradio_app/README_zh-CN.md): 基于 Gradio 的 Web 应用
- [web_demo](./web_demo/README_zh-CN.md): MinerU在线[demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/)本地化部署版本
- ~~[web_demo](./web_demo/README_zh-CN.md): MinerU在线[demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/)本地化部署版本~~(已过时)
- [web_api](./web_api/README.md): 基于 FastAPI 的 Web API
- [multi_gpu](./multi_gpu/README.md): 基于 LitServe 的多 GPU 并行处理
......@@ -28,7 +28,7 @@ app = FastAPI()
pdf_extensions = [".pdf"]
office_extensions = [".ppt", ".pptx", ".doc", ".docx"]
image_extensions = [".png", ".jpg"]
image_extensions = [".png", ".jpg", ".jpeg"]
class MemoryDataWriter(DataWriter):
def __init__(self):
......@@ -128,7 +128,7 @@ def process_file(
Tuple[InferenceResult, PipeResult]: Returns inference result and pipeline result
"""
ds = Union[PymuDocDataset, ImageDataset]
ds: Union[PymuDocDataset, ImageDataset] = None
if file_extension in pdf_extensions:
ds = PymuDocDataset(file_bytes)
elif file_extension in office_extensions:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment