diff --git a/collector/scripts/watch/convert/as_docx.py b/collector/scripts/watch/convert/as_docx.py
index 6d16650e3e5ecf85a84914965d6547e06a3b94a7..33aaaaaeb0b9b619a6aee4c02f428f61e604db8e 100644
--- a/collector/scripts/watch/convert/as_docx.py
+++ b/collector/scripts/watch/convert/as_docx.py
@@ -16,6 +16,10 @@ def as_docx(**kwargs):
data = loader.load()[0]
content = data.page_content
+ if len(content) == 0:
+ print(f"Resulting text content was empty for {filename}{ext}.")
+ return(False, f"No text content found in {filename}{ext}")
+
print(f"-- Working {fullpath} --")
data = {
'id': guid(),
@@ -33,7 +37,9 @@ def as_docx(**kwargs):
write_to_server_documents(data, f"{slugify(filename)}-{data.get('id')}")
move_source(parent_dir, f"{filename}{ext}", remove=remove)
+
print(f"[SUCCESS]: {filename}{ext} converted & ready for embedding.\n")
+ return(True, None)
def as_odt(**kwargs):
parent_dir = kwargs.get('directory', 'hotdir')
@@ -46,6 +52,10 @@ def as_odt(**kwargs):
data = loader.load()[0]
content = data.page_content
+ if len(content) == 0:
+ print(f"Resulting text content was empty for {filename}{ext}.")
+ return(False, f"No text content found in {filename}{ext}")
+
print(f"-- Working {fullpath} --")
data = {
'id': guid(),
@@ -63,4 +73,6 @@ def as_odt(**kwargs):
write_to_server_documents(data, f"{slugify(filename)}-{data.get('id')}")
move_source(parent_dir, f"{filename}{ext}", remove=remove)
+
print(f"[SUCCESS]: {filename}{ext} converted & ready for embedding.\n")
+ return(True, None)
\ No newline at end of file
diff --git a/collector/scripts/watch/convert/as_markdown.py b/collector/scripts/watch/convert/as_markdown.py
index 3e1a3dba1a700b299544dc6bdcb00402c120675f..b7d9fbf6d274249a7f46a4cabb8b408c7f3be26f 100644
--- a/collector/scripts/watch/convert/as_markdown.py
+++ b/collector/scripts/watch/convert/as_markdown.py
@@ -16,6 +16,10 @@ def as_markdown(**kwargs):
data = loader.load()[0]
content = data.page_content
+ if len(content) == 0:
+ print(f"Resulting page content was empty - no text could be extracted from {filename}{ext}.")
+ return(False, f"No text could be extracted from {filename}{ext}.")
+
print(f"-- Working {fullpath} --")
data = {
'id': guid(),
@@ -33,4 +37,6 @@ def as_markdown(**kwargs):
write_to_server_documents(data, f"{slugify(filename)}-{data.get('id')}")
move_source(parent_dir, f"{filename}{ext}", remove=remove)
+
print(f"[SUCCESS]: {filename}{ext} converted & ready for embedding.\n")
+ return(True, None)
diff --git a/collector/scripts/watch/convert/as_mbox.py b/collector/scripts/watch/convert/as_mbox.py
index 96c9b25bb551726a6230a7f89334c6c19308a78a..048fd0e49051932a7f2318b7d19362dc4b486139 100644
--- a/collector/scripts/watch/convert/as_mbox.py
+++ b/collector/scripts/watch/convert/as_mbox.py
@@ -55,5 +55,7 @@ def as_mbox(**kwargs):
}
write_to_server_documents(data, f"{slugify(filename)}-{data.get('id')}")
+
move_source(parent_dir, f"{filename}{ext}", remove=remove)
print(f"[SUCCESS]: {filename}{ext} converted & ready for embedding.\n")
+ return(True, None)
diff --git a/collector/scripts/watch/convert/as_pdf.py b/collector/scripts/watch/convert/as_pdf.py
index c5517332344a991fdd40a4e4890eadbee10fe97c..8fc1d1f3d2c80c952edb4db4a562fedfd956b84b 100644
--- a/collector/scripts/watch/convert/as_pdf.py
+++ b/collector/scripts/watch/convert/as_pdf.py
@@ -19,7 +19,7 @@ def as_pdf(**kwargs):
if len(pages) == 0:
print(f"{fullpath} parsing resulted in no pages - nothing to do.")
- return False
+ return(False, f"No pages found for {filename}{ext}!")
# Set doc to the first page so we can still get the metadata from PyMuPDF but without all the unicode issues.
doc = pages[0]
@@ -31,6 +31,10 @@ def as_pdf(**kwargs):
print(f"-- Parsing content from pg {page.number} --")
page_content += unidecode(page.get_text('text'))
+ if len(page_content) == 0:
+ print(f"Resulting page content was empty - no text could be extracted from the document.")
+ return(False, f"No text content could be extracted from {filename}{ext}!")
+
title = doc.metadata.get('title')
author = doc.metadata.get('author')
subject = doc.metadata.get('subject')
@@ -50,4 +54,6 @@ def as_pdf(**kwargs):
write_to_server_documents(data, f"{slugify(filename)}-{data.get('id')}")
move_source(parent_dir, f"{filename}{ext}", remove=remove)
+
print(f"[SUCCESS]: {filename}{ext} converted & ready for embedding.\n")
+ return(True, None)
diff --git a/collector/scripts/watch/convert/as_text.py b/collector/scripts/watch/convert/as_text.py
index f3389c849c4ed85929668a882df3a3a09689ace8..e6ad85140d88e076ca8f57edccdd64a117c2d6cf 100644
--- a/collector/scripts/watch/convert/as_text.py
+++ b/collector/scripts/watch/convert/as_text.py
@@ -12,6 +12,10 @@ def as_text(**kwargs):
fullpath = f"{parent_dir}/{filename}{ext}"
content = open(fullpath).read()
+ if len(content) == 0:
+ print(f"Resulting text content was empty for {filename}{ext}.")
+ return(False, f"No text content found in {filename}{ext}")
+
print(f"-- Working {fullpath} --")
data = {
'id': guid(),
@@ -28,4 +32,6 @@ def as_text(**kwargs):
write_to_server_documents(data, f"{slugify(filename)}-{data.get('id')}")
move_source(parent_dir, f"{filename}{ext}", remove=remove)
+
print(f"[SUCCESS]: {filename}{ext} converted & ready for embedding.\n")
+ return(True, None)
diff --git a/collector/scripts/watch/process_single.py b/collector/scripts/watch/process_single.py
index f41219eb3837c077cd6f47464dfae54f72a7c6ea..19fc3978d496642ebd5fc4732c2d58c8e01548cf 100644
--- a/collector/scripts/watch/process_single.py
+++ b/collector/scripts/watch/process_single.py
@@ -25,11 +25,11 @@ def process_single(directory, target_doc):
move_source(new_destination_filename=target_doc, failed=True, remove=True)
return (False, f"{fileext} not a supported file type for conversion. It will not be processed.")
- FILETYPES[fileext](
+ # Returns Tuple of (Boolean, String|None) of success status and possible error message.
+ # Error message will display to user.
+ return FILETYPES[fileext](
directory=directory,
filename=filename,
ext=fileext,
remove_on_complete=True # remove source document to save disk space.
- )
-
- return (True, None)
+ )
\ No newline at end of file
diff --git a/frontend/src/components/Modals/MangeWorkspace/Upload/FileUploadProgress/index.jsx b/frontend/src/components/Modals/MangeWorkspace/Upload/FileUploadProgress/index.jsx
index 5883c4b2095e89745d951c877ef72bc7805a974f..8c47581c4f3b9e46f2c8e424a5e2c8dff562c6d9 100644
--- a/frontend/src/components/Modals/MangeWorkspace/Upload/FileUploadProgress/index.jsx
+++ b/frontend/src/components/Modals/MangeWorkspace/Upload/FileUploadProgress/index.jsx
@@ -14,7 +14,8 @@ function FileUploadProgressComponent({
onUploadError,
}) {
const [timerMs, setTimerMs] = useState(10);
- const [status, setStatus] = useState(file?.rejected ? "uploading" : "failed");
+ const [status, setStatus] = useState("pending");
+ const [error, setError] = useState("");
useEffect(() => {
async function uploadFile() {
@@ -31,6 +32,7 @@ function FileUploadProgressComponent({
setStatus("failed");
clearInterval(timer);
onUploadError(data.error);
+ setError(data.error);
} else {
setStatus("complete");
clearInterval(timer);
@@ -58,6 +60,24 @@ function FileUploadProgressComponent({
);
}
+ if (status === "failed") {
+ return (
+ <div className="w-fit px-2 py-2 flex items-center gap-x-4 rounded-lg bg-blue-100 border-blue-600 dark:bg-stone-800 bg-opacity-50 border dark:border-stone-600">
+ <div className="w-6 h-6">
+ <XCircle className="w-6 h-6 stroke-white bg-red-500 rounded-full p-1 w-full h-full" />
+ </div>
+ <div className="flex flex-col">
+ <p className="text-black dark:text-stone-200 text-sm font-mono overflow-x-scroll">
+ {truncate(file.name, 30)}
+ </p>
+ <p className="text-red-700 dark:text-red-400 text-xs font-mono">
+ {error}
+ </p>
+ </div>
+ </div>
+ );
+ }
+
return (
<div className="w-fit px-2 py-2 flex items-center gap-x-4 rounded-lg bg-blue-100 border-blue-600 dark:bg-stone-800 bg-opacity-50 border dark:border-stone-600">
<div className="w-6 h-6">
@@ -77,6 +97,8 @@ function FileUploadProgressComponent({
</div>
</div>
);
+
+ return null;
}
export default memo(FileUploadProgressComponent);