Skip to content

docs(ingest): blank scans and text-free photos fail with E2002 (PRO-2456) - #313

Merged
adityashrivastavaa merged 1 commit into
mainfrom
aditya/pro-2456-blank-image-docs
Oct 6, 2026
Merged

adityashrivastavaa merged 1 commit into
mainfrom
aditya/pro-2456-blank-image-docs

Conversation

@adityashrivastavaa

Copy link
Copy Markdown
Contributor

Part of PRO-2456. Merge only when the companion code ships: hydra-db/hydradb-application#2057 (Go Stage A, which serves POST /context/ingest documents) and hydra-db/cortex-ingestion#911.

What changes for customers

The "Supported file formats" section of ingest-context said:

A scanned page with nothing readable on it, or a photo that happens to contain no text, will index as an empty document rather than fail.

That was never quite true. LiteParse emitted an empty ```text code fence for such pages, and that fence was what got indexed. With the fence fixed, a binary file with no extractable text now ends errored with E2002. Customers see the message "No text content could be extracted from your file. Please ensure it isn't empty or image-only." It is terminal: the same file gives the same result. A multi-page scan with readable text on any page still indexes normally.

Changes

  • api-reference/v2/endpoint/ingest-context.mdx: replace that sentence with the actual behaviour, linking to the error code.
  • api-reference/v2/error-responses.mdx: add an E2002 row to the ingestion error-codes table (meaning, user message, terminal).

Not changed: connector and app-source docs. The other PRO-2456 work, Gemini transcription and description of connector image attachments, changes no API surface or behaviour that customers call directly.

🤖 Generated with Claude Code

@mintlify

mintlify Bot commented Oct 6, 2026 •

Copy link
Copy Markdown
Contributor

Preview deployment for your docs. Learn more about Mintlify Previews.

Project Status Preview Updated
cortex-ai 🟢 Ready View Preview Oct 6, 2026, 5:00 AM

💡 Tip: Enable Automations to automatically generate PRs for you.

@github-actions

github-actions Bot commented Oct 6, 2026

Copy link
Copy Markdown

✅ Mintlify Hygiene

No issues found.

@greptile-apps

greptile-apps Bot commented Oct 6, 2026 •

Copy link
Copy Markdown
Contributor

RetriggerConfidence Score: 5/5

[Low risk] Documents error code behavior in the API reference.

The documentation changes appear safe to merge when the companion code ships, as the PR description requires.

Summary

The PR updates the ingestion documentation to say that scans and images with no extractable text end in terminal E2002, rather than indexing as empty documents.

  • Adds the error’s meaning, customer-facing message, and terminal status to the ingestion error-code table.

Reviews (2) · Last reviewed commit: "docs(ingest): blank scans and text-free ..."

@openhack-agent

openhack-agent Bot commented Oct 6, 2026 •

Copy link
Copy Markdown

✅ OpenHack Summary

Security review of docs(ingest): blank scans and text-free photos fail with E2002 (PRO-2456). 2 changed files; 0 findings at or above the low reporting threshold.

P1: Critical 0   P2: High 0   P3: Medium 0   P4: Low 0

Confidence Score: 5/5

No reportable security findings were detected in this scan.

Security merge-readiness rubric: 1 = critical, 2 = high, 3 = medium, 4 = low, 5 = no reportable findings. This score reflects scan findings, not a guarantee of correctness or complete coverage.

Files Needing Attention: None

Important Files Changed
  • api-reference/v2/endpoint/ingest-context.mdx (modified)
  • api-reference/v2/error-responses.mdx (modified)

Last reviewed commit: 4fb2032 · View review on OpenHack


TIP: Mention @openhack-agent in a PR comment to request a review or ask a question. Use @openhack-agent fix all for every finding, or @openhack-agent fix unresolved threads for open review threads only.

@openhack-agent openhack-agent Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

OpenHack reviewed this commit. See the OpenHack Summary for the confidence score and fix actions.

…456)

The supported-formats section said a scan or photo with no readable text
'will index as an empty document rather than fail'. It actually indexed an
empty OCR code fence; with that fixed, such a file now ends errored with E2002
('No text content could be extracted'), which is terminal. Document that, and
add E2002 to the ingestion error-code table.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Signed-off-by: Aditya Shrivastava <aditya@hydradb.com>
@adityashrivastavaa
adityashrivastavaa merged commit e0d6a3b into main Oct 6, 2026
8 checks passed
@adityashrivastavaa
adityashrivastavaa deleted the aditya/pro-2456-blank-image-docs branch October 6, 2026 21:51

This branch was successfully deployed

1 active deployment
staging — 4fb20329 Deployed Oct 6, 2026 by mintlify[bot]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants