run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 01:15:06 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

TS SDK - Error parsing MSFT DOCX and PPTX File Types - I suspect LlamaParseReader is applying wrong MIME Type #290

New Issue
Closed
opened 2026-02-16 00:17:23 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 00:17:23 -05:00
Owner
Copy Link
Copy Source

Originally created by @ajpanyteam on GitHub (Oct 8, 2024).

Describe the bug

Using the llamaIndex TS SDK v0.6.17.

llamaParse works for PDF and XLSX files but fails for PPTX and DOCX file types only.

The following error message is received on loadDataAsContent: Error while parsing the file: Failed to parse the file f827....

I suspect this is related to https://github.com/run-llama/LlamaIndexTS/issues/1006 because I added a breakpoint to LlamaParseReader and saw a different MIME Type get applied, details are in Additional Content section below.

Write a concise description of what the bug is

Using the following code returns “Error while parsing the file: Failed to parse the file”:

      const file = storage.bucket(process.env.GCP_BUCKET).file(fileId);
      const [buffer] = await file.download();

      const getMetadata = await file.getMetadata();
      console.log(getMetadata[0].contentType)

      const reader = new LlamaParseReader({
        resultType: "markdown",
        skipDiagonalText: true,
        verbose: true,
      });

      const unt8Array = new Uint8Array(buffer);
      const documents = await reader.loadDataAsContent(unt8Array); // --->  Error while parsing the file: Failed to parse the file: c8e8b079-f3aa-4786-bfe3-e9b3981812cf, status: ERROR

Files

  • wget "https://meetings.wmo.int/Cg-19/PublishingImages/SitePages/FINAC-43/7%20-%20EC-77-Doc%205%20Financial%20Statements%20for%202022%20(FINAC).pptx" -O data/presentation.ppt
    ppx source file from llamaParse github

  • The error occurs with all PPTX files I have tested so far.

Job ID
If you have it, please provide the ID of the job you ran.
You can find it here: https://cloud.llamaindex.ai/parse in the "History" tab.

  • ac0c1b4a-915f-4d00-9340-25506d085f33
  • f8275764-361f-4fd9-ac6d-634193c556b2
  • c8e8b079-f3aa-4786-bfe3-e9b3981812cf

Above jobIds are from my console output. My cloud.llamaindex.ai history tab does not have these jobs.

Screenshots
Feel free to also provide screenshots if relevant.

image

Client:
Please remove untested options:

  • Frontend (cloud.llamaindex.ai)
  • Typescript Library "llamaindex": "0.6.17"

Options
What options did you use? Multimodal, fast mode, parsing instructions, etc.

  • Refer to code sample above.

Additional context

  • XLST, DOCS and PDF fileswork just fine.
  • When I use cloud.llamaindex.ai to parse the PPTX file, it only works with Accurate mode enabled (not surprisingly, as it uses OCR) and is able to process the referenced PPTX file. The UI states, “Default mode, no need to set accurate_mode=true on API” so I assume the llamaParse settings I am using are correct. I could not find any option to set accurate_mode, thus I assume it is set as default.
  • Digging into the SDK, I added a breakpoint inside the SDK on LlamaParseReader createJob. The PPT MimeType applied is application/vnd.oasis.opendocument.spreadsheet
    image

Sample of a pptx

image
Originally created by @ajpanyteam on GitHub (Oct 8, 2024). **Describe the bug** Using the llamaIndex TS SDK v0.6.17. llamaParse works for PDF and XLSX files but fails for PPTX and DOCX file types only. The following error message is received on `loadDataAsContent`: _Error while parsing the file: Failed to parse the file f827...._ I suspect this is related to https://github.com/run-llama/LlamaIndexTS/issues/1006 because I added a breakpoint to LlamaParseReader and saw a different MIME Type get applied, details are in **Additional Content** section below. **Write a concise description of what the bug is** Using the following code returns “Error while parsing the file: Failed to parse the file”: ``` const file = storage.bucket(process.env.GCP_BUCKET).file(fileId); const [buffer] = await file.download(); const getMetadata = await file.getMetadata(); console.log(getMetadata[0].contentType) const reader = new LlamaParseReader({ resultType: "markdown", skipDiagonalText: true, verbose: true, }); const unt8Array = new Uint8Array(buffer); const documents = await reader.loadDataAsContent(unt8Array); // ---> Error while parsing the file: Failed to parse the file: c8e8b079-f3aa-4786-bfe3-e9b3981812cf, status: ERROR ``` **Files** - ```wget "https://meetings.wmo.int/Cg-19/PublishingImages/SitePages/FINAC-43/7%20-%20EC-77-Doc%205%20Financial%20Statements%20for%202022%20(FINAC).pptx" -O data/presentation.ppt``` [ppx source file from llamaParse github](https://github.com/run-llama/llama_parse/blob/main/examples/other_files/demo_ppt_financial.ipynb) - The error occurs with all PPTX files I have tested so far. **Job ID** If you have it, please provide the ID of the job you ran. You can find it here: https://cloud.llamaindex.ai/parse in the "History" tab. - ac0c1b4a-915f-4d00-9340-25506d085f33 - f8275764-361f-4fd9-ac6d-634193c556b2 - c8e8b079-f3aa-4786-bfe3-e9b3981812cf Above jobIds are from my console output. My cloud.llamaindex.ai history tab does not have these jobs. **Screenshots** Feel free to also provide screenshots if relevant. <img width="838" alt="image" src="https://github.com/user-attachments/assets/c6f2318c-9108-4931-9543-57455c795c1b"> **Client:** Please remove untested options: - Frontend (cloud.llamaindex.ai) - Typescript Library ```"llamaindex": "0.6.17"``` **Options** What options did you use? Multimodal, fast mode, parsing instructions, etc. - Refer to code sample above. **Additional context** - XLST, DOCS and PDF fileswork just fine. - When I use cloud.llamaindex.ai to parse the PPTX file, it only works with Accurate mode enabled (not surprisingly, as it uses OCR) and is able to process the referenced PPTX file. The UI states, “_Default mode, no need to set accurate_mode=true on API_” so I assume the llamaParse settings I am using are correct. I could not find any option to set accurate_mode, thus I assume it is set as default. - Digging into the SDK, I added a breakpoint inside the SDK on LlamaParseReader `createJob`. The PPT MimeType applied is **application/vnd.oasis.opendocument.spreadsheet** ![image](https://github.com/user-attachments/assets/85af9234-70b6-47c2-9ebb-6be1821bcd1c) Sample of a pptx <img width="1048" alt="image" src="https://github.com/user-attachments/assets/ed4a5f27-41bd-4f8d-9e6a-4e91b1c96c15">
yindo added the bug label 2026-02-16 00:17:23 -05:00
yindo closed this issue 2026-02-16 00:17:23 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#290
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?