-
Notifications
You must be signed in to change notification settings - Fork 7.9k
Fix ratelimit errors during document parsing #6413
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Fix ratelimit errors during document parsing #6413
Conversation
This update specifically targets DOCX files, ensuring table-context association for RAG systems.
…ring document parsing When using the online large model API knowledge base to extract knowledge graphs, frequent Rate Limit Errors were triggered, causing document parsing to fail. This commit fixes the issue by optimizing API calls in the following way: Added exponential backoff and jitter to the API call to reduce the frequency of Rate Limit Errors.
|
@fansir LGTM. I would suggest do more: |
Implementing tenant-based concurrency control using Redis is a solid suggestion for managing fairness among tenants. However, it does not fully address the rate-limiting challenges posed by large model service providers, as their throttling policies vary significantly. For instance, some providers enforce time-based limits (e.g., requests per minute) or token-based quotas, which cannot be directly managed through concurrency control alone. To handle these provider-specific constraints effectively, it is essential to combine tenant-level concurrency control with adaptive backoff mechanisms. For example: When a provider's rate limit is triggered, the system should implement exponential backoff or retry-after strategies to comply with the provider's policy. In summary, provider-aware rate limiting and backoff mechanisms are necessary to fully address the diverse throttling requirements of large model service providers. |
093c836 to
0cf391d
Compare
0cf391d to
c32cdab
Compare
| # For non-rate limit errors or the last attempt, return an error message | ||
| if attempt == self.max_retries - 1: | ||
| error_code = ERROR_MAX_RETRIES | ||
| return f"{ERROR_PREFIX}: {error_code} - {str(e)}", 0 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Raise exception (the original one, or wrap it) so that trio can notice the failure.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Regarding this suggestion, I would like to confirm something. I noticed that the design of the pre-modified code handles errors by returning error messages in a specific format, rather than using the exception mechanism. If we change it to throw an exception, it would require the caller to handle this exception; otherwise, the program might crash.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Oh, my mistake.
…1679) Bumps [axios](https://github.com/axios/axios) from 0.27.2 to 1.7.2. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/axios/axios/releases">axios's releases</a>.</em></p> <blockquote> <h2>Release v1.7.2</h2> <h2>Release notes:</h2> <h3>Bug Fixes</h3> <ul> <li><strong>fetch:</strong> enhance fetch API detection; (<a href="https://redirect.github.com/axios/axios/issues/6413">#6413</a>) (<a href="https://github.com/axios/axios/commit/4f79aef81b7c4644328365bfc33acf0a9ef595bc">4f79aef</a>)</li> </ul> <h3>Contributors to this release</h3> <ul> <li><!-- raw HTML omitted --> <a href="https://github.com/DigitalBrainJS" title="+3/-3 ([infiniflow#6413](axios/axios#6413) )">Dmitriy Mozgovoy</a></li> </ul> <h2>Release v1.7.1</h2> <h2>Release notes:</h2> <h3>Bug Fixes</h3> <ul> <li><strong>fetch:</strong> fixed ReferenceError issue when TextEncoder is not available in the environment; (<a href="https://redirect.github.com/axios/axios/issues/6410">#6410</a>) (<a href="https://github.com/axios/axios/commit/733f15fe5bd2d67e1fadaee82e7913b70d45dc5e">733f15f</a>)</li> </ul> <h3>Contributors to this release</h3> <ul> <li><!-- raw HTML omitted --> <a href="https://github.com/DigitalBrainJS" title="+14/-9 ([infiniflow#6410](axios/axios#6410) )">Dmitriy Mozgovoy</a></li> </ul> <h2>Release v1.7.0</h2> <h2>Release notes:</h2> <h3>Features</h3> <ul> <li><strong>adapter:</strong> add fetch adapter; (<a href="https://redirect.github.com/axios/axios/issues/6371">#6371</a>) (<a href="https://github.com/axios/axios/commit/a3ff99b59d8ec2ab5dd049e68c043617a4072e42">a3ff99b</a>)</li> </ul> <h3>Bug Fixes</h3> <ul> <li><strong>core/axios:</strong> handle un-writable error stack (<a href="https://redirect.github.com/axios/axios/issues/6362">#6362</a>) (<a href="https://github.com/axios/axios/commit/81e0455b7b57fbaf2be16a73ebe0e6591cc6d8f9">81e0455</a>)</li> </ul> <h3>Contributors to this release</h3> <ul> <li><!-- raw HTML omitted --> <a href="https://github.com/DigitalBrainJS" title="+1015/-127 ([infiniflow#6371](axios/axios#6371) )">Dmitriy Mozgovoy</a></li> <li><!-- raw HTML omitted --> <a href="https://github.com/jasonsaayman" title="+30/-14 ()">Jay</a></li> <li><!-- raw HTML omitted --> <a href="https://github.com/alexandre-abrioux" title="+56/-6 ([infiniflow#6362](axios/axios#6362) )">Alexandre ABRIOUX</a></li> </ul> <h2>Release v1.7.0-beta.2</h2> <h2>Release notes:</h2> <h3>Bug Fixes</h3> <ul> <li><strong>fetch:</strong> capitalize HTTP method names; (<a href="https://redirect.github.com/axios/axios/issues/6395">#6395</a>) (<a href="https://github.com/axios/axios/commit/ad3174a3515c3c2573f4bcb94818d582826f3914">ad3174a</a>)</li> <li><strong>fetch:</strong> fix & optimize progress capturing for cases when the request data has a nullish value or zero data length (<a href="https://redirect.github.com/axios/axios/issues/6400">#6400</a>) (<a href="https://github.com/axios/axios/commit/95a3e8e346cfd6a5548e171f2341df3235d0e26b">95a3e8e</a>)</li> <li><strong>fetch:</strong> fix headers getting from a stream response; (<a href="https://redirect.github.com/axios/axios/issues/6401">#6401</a>) (<a href="https://github.com/axios/axios/commit/870e0a76f60d0094774a6a63fa606eec52a381af">870e0a7</a>)</li> </ul> <h3>Contributors to this release</h3> <ul> <li><!-- raw HTML omitted --> <a href="https://github.com/DigitalBrainJS" title="+99/-46 ([infiniflow#6405](axios/axios#6405) [infiniflow#6404](axios/axios#6404) [infiniflow#6401](axios/axios#6401) [infiniflow#6400](axios/axios#6400) [infiniflow#6395](axios/axios#6395) )">Dmitriy Mozgovoy</a></li> </ul> <h2>Release v1.7.0-beta.1</h2> <h2>Release notes:</h2> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/axios/axios/blob/v1.x/CHANGELOG.md">axios's changelog</a>.</em></p> <blockquote> <h2><a href="https://github.com/axios/axios/compare/v1.7.1...v1.7.2">1.7.2</a> (2024-05-21)</h2> <h3>Bug Fixes</h3> <ul> <li><strong>fetch:</strong> enhance fetch API detection; (<a href="https://redirect.github.com/axios/axios/issues/6413">#6413</a>) (<a href="https://github.com/axios/axios/commit/4f79aef81b7c4644328365bfc33acf0a9ef595bc">4f79aef</a>)</li> </ul> <h3>Contributors to this release</h3> <ul> <li><!-- raw HTML omitted --> <a href="https://github.com/DigitalBrainJS" title="+3/-3 ([infiniflow#6413](axios/axios#6413) )">Dmitriy Mozgovoy</a></li> </ul> <h2><a href="https://github.com/axios/axios/compare/v1.7.0...v1.7.1">1.7.1</a> (2024-05-20)</h2> <h3>Bug Fixes</h3> <ul> <li><strong>fetch:</strong> fixed ReferenceError issue when TextEncoder is not available in the environment; (<a href="https://redirect.github.com/axios/axios/issues/6410">#6410</a>) (<a href="https://github.com/axios/axios/commit/733f15fe5bd2d67e1fadaee82e7913b70d45dc5e">733f15f</a>)</li> </ul> <h3>Contributors to this release</h3> <ul> <li><!-- raw HTML omitted --> <a href="https://github.com/DigitalBrainJS" title="+14/-9 ([infiniflow#6410](axios/axios#6410) )">Dmitriy Mozgovoy</a></li> </ul> <h1><a href="https://github.com/axios/axios/compare/v1.7.0-beta.2...v1.7.0">1.7.0</a> (2024-05-19)</h1> <h3>Features</h3> <ul> <li><strong>adapter:</strong> add fetch adapter; (<a href="https://redirect.github.com/axios/axios/issues/6371">#6371</a>) (<a href="https://github.com/axios/axios/commit/a3ff99b59d8ec2ab5dd049e68c043617a4072e42">a3ff99b</a>)</li> </ul> <h3>Bug Fixes</h3> <ul> <li><strong>core/axios:</strong> handle un-writable error stack (<a href="https://redirect.github.com/axios/axios/issues/6362">#6362</a>) (<a href="https://github.com/axios/axios/commit/81e0455b7b57fbaf2be16a73ebe0e6591cc6d8f9">81e0455</a>)</li> </ul> <h3>Contributors to this release</h3> <ul> <li><!-- raw HTML omitted --> <a href="https://github.com/DigitalBrainJS" title="+1015/-127 ([infiniflow#6371](axios/axios#6371) )">Dmitriy Mozgovoy</a></li> <li><!-- raw HTML omitted --> <a href="https://github.com/jasonsaayman" title="+30/-14 ()">Jay</a></li> <li><!-- raw HTML omitted --> <a href="https://github.com/alexandre-abrioux" title="+56/-6 ([infiniflow#6362](axios/axios#6362) )">Alexandre ABRIOUX</a></li> </ul> <h1><a href="https://github.com/axios/axios/compare/v1.7.0-beta.1...v1.7.0-beta.2">1.7.0-beta.2</a> (2024-05-19)</h1> <h3>Bug Fixes</h3> <ul> <li><strong>fetch:</strong> capitalize HTTP method names; (<a href="https://redirect.github.com/axios/axios/issues/6395">#6395</a>) (<a href="https://github.com/axios/axios/commit/ad3174a3515c3c2573f4bcb94818d582826f3914">ad3174a</a>)</li> <li><strong>fetch:</strong> fix & optimize progress capturing for cases when the request data has a nullish value or zero data length (<a href="https://redirect.github.com/axios/axios/issues/6400">#6400</a>) (<a href="https://github.com/axios/axios/commit/95a3e8e346cfd6a5548e171f2341df3235d0e26b">95a3e8e</a>)</li> <li><strong>fetch:</strong> fix headers getting from a stream response; (<a href="https://redirect.github.com/axios/axios/issues/6401">#6401</a>) (<a href="https://github.com/axios/axios/commit/870e0a76f60d0094774a6a63fa606eec52a381af">870e0a7</a>)</li> </ul> <h3>Contributors to this release</h3> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href="https://github.com/axios/axios/commit/0e4f9fa29077ebee4499facea6be1492b42e8a26"><code>0e4f9fa</code></a> chore(release): v1.7.2 (<a href="https://redirect.github.com/axios/axios/issues/6414">#6414</a>)</li> <li><a href="https://github.com/axios/axios/commit/4f79aef81b7c4644328365bfc33acf0a9ef595bc"><code>4f79aef</code></a> fix(fetch): enhance fetch API detection; (<a href="https://redirect.github.com/axios/axios/issues/6413">#6413</a>)</li> <li><a href="https://github.com/axios/axios/commit/67d1373131962d1f1f5b8d91f9a2f80ed3923bc8"><code>67d1373</code></a> chore(release): v1.7.1 (<a href="https://redirect.github.com/axios/axios/issues/6411">#6411</a>)</li> <li><a href="https://github.com/axios/axios/commit/733f15fe5bd2d67e1fadaee82e7913b70d45dc5e"><code>733f15f</code></a> fix(fetch): fixed ReferenceError issue when TextEncoder is not available in t...</li> <li><a href="https://github.com/axios/axios/commit/3041c61adaaac6d2c43eba28c134e7f4d43ab012"><code>3041c61</code></a> [Release] v1.7.0 (<a href="https://redirect.github.com/axios/axios/issues/6408">#6408</a>)</li> <li><a href="https://github.com/axios/axios/commit/18b13cbaef66d8c266cf681165afe31787420100"><code>18b13cb</code></a> chore(docs): add fetch adapter docs; (<a href="https://redirect.github.com/axios/axios/issues/6407">#6407</a>)</li> <li><a href="https://github.com/axios/axios/commit/e62099bc8b640acf47fba639366bbcd3bf87f831"><code>e62099b</code></a> fix(fetch): fixed a possible memory leak in the AbortController for the strea...</li> <li><a href="https://github.com/axios/axios/commit/b49aa8e3d837c36e4728a9fa8a5e23a1162e96ec"><code>b49aa8e</code></a> chore(release): v1.7.0-beta.2 (<a href="https://redirect.github.com/axios/axios/issues/6403">#6403</a>)</li> <li><a href="https://github.com/axios/axios/commit/d57f03a77fef1eb3cd9a17e2973c4305e105a42e"><code>d57f03a</code></a> chore(ci): bump create-pull-request version to fix a bug; (<a href="https://redirect.github.com/axios/axios/issues/6405">#6405</a>)</li> <li><a href="https://github.com/axios/axios/commit/097b0d18e93d12c53b77741d6bfdc8a1fc11828b"><code>097b0d1</code></a> chore(ci): add tag resolution for npm releases based on package version; (<a href="https://redirect.github.com/axios/axios/issues/6404">#6404</a>)</li> <li>Additional commits viewable in <a href="https://github.com/axios/axios/compare/v0.27.2...v1.7.2">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/infiniflow/ragflow/network/alerts). </details> Signed-off-by: dependabot[bot] <[email protected]> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

What problem does this PR solve?
When using the online large model API knowledge base to extract knowledge graphs, frequent Rate Limit Errors were triggered,
causing document parsing to fail. This commit fixes the issue by optimizing API calls in the following way:
Added exponential backoff and jitter to the API call to reduce the frequency of Rate Limit Errors.
Type of change