Zipstack / Zipstack/unstract

fix: [ISSUE] "Error fetching data and indexing: [Errno 2] No such file or directory: '/data/INFILE.pdf'" in API workflow execution

Open
#595 16 comments 0 reactions 1 assignee View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Python
Stars
7.2k
Forks
718
Avg merge
3d 1h
Merged PRs (30d)
23

Description

Describe the bug

Following "Getting Started" instructions, but got an error in API workflow. Always the same errors happen.

Error fetching data and indexing: [Errno 2] No such file or directory: '/data/INFILE.pdf'

To reproduce

Following "Getting Started" instructions, except:

  • using Japanese invoice PDF
  • change prompts a little to match with invoice documents.

Errors happens:

  • create API workflow and reqeust API with Postman (checked logs via workflow)
  • and also "Run Workflow" with some PDFs in workflow screen.

got the same error always.

Expected behavior

  • API workflow returns correct parsed data.
  • "Run Workflow" works correctly and return parsed data.

Environment details

  • Version: commit 830e56382b5725590ccc1ea3f21fa644f62e070e (tag: v0.81.0)
  • OS: macOS 13.6
  • Docker: Docker Desktop for Mac 4.31.0
  • LLM: OpenAI gpt-4o-mini
  • Embeddings: OpenAI
  • VectorDB: Qdrant Cloud
  • Text Extractor: Llama Parse

Additional context

I have 3 sample PDF.
Parsing all of them works perfectly in Prompt Studio.
OTOH, in both API and Workflow, Parsing all of above always failed.

Screenshots

API reqeust from Postman
SS_ 2024-08-19 22 50 41

and logs

59b5ece3a177-20240819

"Run Workflow"

9babcf679378-20240819

Prompt Studio works.
SS_ 2024-08-19 22 12 27

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.