MindWorkAI/AI-Studio
MindWorkAI/AI-Studio
1
0
Fork 0
mirror of https://github.com/MindWorkAI/AI-Studio.git synced 2025-07-27 22:02:56 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Exposed image extraction state to file data streaming & passing this state to rust for optimizations

Browse Source
This commit is contained in:
Thorsten Sommer 2025-06-30 20:54:12 +02:00
parent a17f39d28e
commit 5c05d3df3c
Signed by: tsommer
GPG Key ID: 371BBA77A02C0108
2 changed files with 19 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
app/MindWork AI Studio/Tools/Services/RustService.Retrieval.cs
View File

@ -5,10 +5,10 @@ namespace AIStudio.Tools.Services;
public sealed partial class RustService
{
public async Task<string> ReadArbitraryFileData(string path, int maxChunks)
public async Task<string> ReadArbitraryFileData(string path, int maxChunks, bool extractImages = false)
{
var streamId = Guid.NewGuid().ToString();
var requestUri = $"/retrieval/fs/extract?path={Uri.EscapeDataString(path)}&stream_id={streamId}";
var requestUri = $"/retrieval/fs/extract?path={Uri.EscapeDataString(path)}&stream_id={streamId}&extract_images={extractImages}";
var request = new HttpRequestMessage(HttpMethod.Get, requestUri);
var response = await this.http.SendAsync(request, HttpCompletionOption.ResponseHeadersRead);
@ -37,7 +37,7 @@ public sealed partial class RustService
var sseEvent = JsonSerializer.Deserialize<ContentStreamSseEvent>(jsonContent);
if (sseEvent is not null)
{
var content = ContentStreamSseHandler.ProcessEvent(sseEvent, false);
var content = ContentStreamSseHandler.ProcessEvent(sseEvent, extractImages);
if(content is not null)
resultBuilder.AppendLine(content);

26
runtime/src/file_data.rs
View File

@ -81,10 +81,10 @@ const IMAGE_SEGMENT_SIZE_IN_CHARS: usize = 8_192; // equivalent to ~ 5500 token
type Result<T> = std::result::Result<T, Box<dyn std::error::Error + Send + Sync>>;
type ChunkStream = Pin<Box<dyn Stream<Item = Result<Chunk>> + Send>>;
#[get("/retrieval/fs/extract?<path>&<stream_id>")]
pub async fn extract_data(_token: APIToken, path: String, stream_id: String, mut end: Shutdown) -> EventStream![] {
#[get("/retrieval/fs/extract?<path>&<stream_id>&<extract_images>")]
pub async fn extract_data(_token: APIToken, path: String, stream_id: String, extract_images: bool, mut end: Shutdown) -> EventStream![] {
EventStream! {
let stream_result = stream_data(&path).await;
let stream_result = stream_data(&path, extract_images).await;
let id_ref = &stream_id;
match stream_result {
@ -116,7 +116,7 @@ pub async fn extract_data(_token: APIToken, path: String, stream_id: String, mut
}
}
async fn stream_data(file_path: &str) -> Result<ChunkStream> {
async fn stream_data(file_path: &str, extract_images: bool) -> Result<ChunkStream> {
if !Path::new(file_path).exists() {
error!("File does not exist: '{file_path}'");
return Err("File does not exist.".into());
@ -133,14 +133,14 @@ async fn stream_data(file_path: &str) -> Result<ChunkStream> {
let ext = file_path.split('.').next_back().unwrap_or("");
debug!("Extracting data from file: '{file_path}', format: '{fmt:?}', extension: '{ext}'");
let stream = match ext {
DOCX | ODT => {
let from = if ext == DOCX { "docx" } else { "odt" };
convert_with_pandoc(file_path, from, TO_MARKDOWN).await?
}
"pptx" => stream_pptx(file_path).await?,
"pptx" => stream_pptx(file_path, extract_images).await?,
"xlsx" | "ods" | "xls" | "xlsm" | "xlsb" | "xla" | "xlam" => {
stream_spreadsheet_as_csv(file_path).await?
@ -163,7 +163,13 @@ async fn stream_data(file_path: &str) -> Result<ChunkStream> {
Kind::Ebook => return Err("Ebooks not yet supported".into()),
Kind::Image => chunk_image(file_path).await?,
Kind::Image => {
if !extract_images {
return Err("Image extraction is disabled.".into());
}
chunk_image(file_path).await?
},
Kind::Other => match fmt {
FileFormat::HypertextMarkupLanguage => {
@ -175,7 +181,7 @@ async fn stream_data(file_path: &str) -> Result<ChunkStream> {
Kind::Presentation => match fmt {
FileFormat::OfficeOpenXmlPresentation => {
stream_pptx(file_path).await?
stream_pptx(file_path, extract_images).await?
},
_ => stream_text_file(file_path).await?,
@ -334,11 +340,11 @@ async fn chunk_image(file_path: &str) -> Result<ChunkStream> {
Ok(Box::pin(stream))
}
async fn stream_pptx(file_path: &str) -> Result<ChunkStream> {
async fn stream_pptx(file_path: &str, extract_images: bool) -> Result<ChunkStream> {
let path = Path::new(file_path).to_owned();
let parser_config = ParserConfig::builder()
.extract_images(true)
.extract_images(extract_images)
.compress_images(true)
.quality(75)
.image_handling_mode(ImageHandlingMode::Manually)