René's URL Explorer Experiment


Title: feat(llm): stop reading images and PDFs as garbage in headless extract by yaanfpv · Pull Request #1110 · Graphify-Labs/graphify · GitHub

Open Graph Title: feat(llm): stop reading images and PDFs as garbage in headless extract by yaanfpv · Pull Request #1110 · Graphify-Labs/graphify

X Title: feat(llm): stop reading images and PDFs as garbage in headless extract by yaanfpv · Pull Request #1110 · Graphify-Labs/graphify

Description: AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph. - feat(llm): stop reading images and PDFs as garbage in headless extract by yaanfpv · Pull Request #1110 · Graphify-Labs/graphify

Open Graph Description: What this does Headless graphify extract feeds every semantic file through _read_files, which does path.read_text(encoding="utf-8", errors="replace"). That is fine for markdown ...

X Description: What this does Headless graphify extract feeds every semantic file through _read_files, which does path.read_text(encoding="utf-8", errors="replace"). That is fi...

Opengraph URL: https://github.com/Graphify-Labs/graphify/pull/1110

X: @github

direct link

Domain: github.com

route-pattern/:user_id/:repository/pull/*id(.:format)
route-controllerpull_requests
route-actionshow
fetch-noncev2:57a7d841-4a8d-e9e8-af78-3f076fcb3bae
current-catalog-service-hashae870bc5e265a340912cde392f23dad3671a0a881730ffdadd82f2f57d81641b
request-id9DB2:1E19D3:F9FFD6:15AAA25:6A4BE96E
html-safe-nonce5b0bc74d02147e9b934fb1e6a53060535a080d203da04d6b330e8175265f8e6d
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiI5REIyOjFFMTlEMzpGOUZGRDY6MTVBQUEyNTo2QTRCRTk2RSIsInZpc2l0b3JfaWQiOiI3MTY4ODY4MDI0NTA1MzMwMDMwIiwicmVnaW9uX2VkZ2UiOiJpYWQiLCJyZWdpb25fcmVuZGVyIjoiaWFkIn0=
visitor-hmac4ec28d46273a513838714fd23fd15a537a171eb965c24bc36435db671fcaeba9
hovercard-subject-tagpull_request:3786185338
github-keyboard-shortcutsrepository,pull-request-list,pull-request-conversation,pull-request-files-changed,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location///pull_requests/show
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/Graphify-Labs/graphify/pull/1110
twitter:imagehttps://opengraph.githubassets.com/3bd51740b29592e8055c7c664a604231846857addd026b0260b0c4c151695d44/Graphify-Labs/graphify/pull/1110
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/3bd51740b29592e8055c7c664a604231846857addd026b0260b0c4c151695d44/Graphify-Labs/graphify/pull/1110
og:image:altWhat this does Headless graphify extract feeds every semantic file through _read_files, which does path.read_text(encoding="utf-8", errors="replace"). That is fine for markdown ...
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
og:author:usernameyaanfpv
hostnamegithub.com
expected-hostnamegithub.com
None0f5d3ba365b3985d75c32a5957c8635488d58dcf027ae6ae958eee7edaa306a2
turbo-cache-controlno-cache
go-importgithub.com/Graphify-Labs/graphify git https://github.com/Graphify-Labs/graphify.git
octolytics-dimension-user_id297659074
octolytics-dimension-user_loginGraphify-Labs
octolytics-dimension-repository_id1200597263
octolytics-dimension-repository_nwoGraphify-Labs/graphify
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id1200597263
octolytics-dimension-repository_network_root_nwoGraphify-Labs/graphify
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
releasef24da9b76b42d77b0bb458f810509565e9ba5f1a
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://github.com/Graphify-Labs/graphify/pull/1110#start-of-content
https://github.com/
Sign in https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FGraphify-Labs%2Fgraphify%2Fpull%2F1110
GitHub CopilotWrite better code with AIhttps://github.com/features/copilot
GitHub Copilot appDirect agents from issue to mergehttps://github.com/features/ai/github-app
MCP RegistryNewIntegrate external toolshttps://github.com/mcp
ActionsAutomate any workflowhttps://github.com/features/actions
CodespacesInstant dev environmentshttps://github.com/features/codespaces
IssuesPlan and track workhttps://github.com/features/issues
Code ReviewManage code changeshttps://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilitieshttps://github.com/security/advanced-security
Code securitySecure your code as you buildhttps://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they starthttps://github.com/security/advanced-security/secret-protection
Why GitHubhttps://github.com/why-github
Documentationhttps://docs.github.com
Bloghttps://github.blog
Changeloghttps://github.blog/changelog
Marketplacehttps://github.com/marketplace
View all featureshttps://github.com/features
Enterpriseshttps://github.com/enterprise
Small and medium teamshttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
App Modernizationhttps://github.com/solutions/use-case/app-modernization
DevSecOpshttps://github.com/solutions/use-case/devsecops
DevOpshttps://github.com/solutions/use-case/devops
CI/CDhttps://github.com/solutions/use-case/ci-cd
View all use caseshttps://github.com/solutions/use-case
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
View all industrieshttps://github.com/solutions/industry
View all solutionshttps://github.com/solutions
AIhttps://github.com/resources/articles?topic=ai
Software Developmenthttps://github.com/resources/articles?topic=software-development
DevOpshttps://github.com/resources/articles?topic=devops
Securityhttps://github.com/resources/articles?topic=security
View all topicshttps://github.com/resources/articles
Customer storieshttps://github.com/customer-stories
Events & webinarshttps://github.com/resources/events
Ebooks & reportshttps://github.com/resources/whitepapers
Business insightshttps://github.com/solutions/executive-insights
GitHub Skillshttps://skills.github.com
Documentationhttps://docs.github.com
Customer supporthttps://support.github.com
Community forumhttps://github.com/orgs/community/discussions
Trust centerhttps://github.com/trust-center
Partnershttps://github.com/partners
View all resourceshttps://github.com/resources
GitHub SponsorsFund open source developershttps://github.com/sponsors
Security Labhttps://securitylab.github.com
Maintainer Communityhttps://maintainers.github.com
Acceleratorhttps://github.com/accelerator
GitHub Starshttps://stars.github.com
Archive Programhttps://archiveprogram.github.com
Topicshttps://github.com/topics
Trendinghttps://github.com/trending
Collectionshttps://github.com/collections
Enterprise platformAI-powered developer platformhttps://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security featureshttps://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/premium-support
Pricinghttps://github.com/pricing
Search syntax tipshttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentationhttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FGraphify-Labs%2Fgraphify%2Fpull%2F1110
Sign up https://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E%2Fpull_requests%2Fshow&source=header-repo&source_repo=Graphify-Labs%2Fgraphify
Reloadhttps://github.com/Graphify-Labs/graphify/pull/1110
Reloadhttps://github.com/Graphify-Labs/graphify/pull/1110
Reloadhttps://github.com/Graphify-Labs/graphify/pull/1110
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
Graphify-Labs https://github.com/Graphify-Labs
graphifyhttps://github.com/Graphify-Labs/graphify
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
Notifications https://github.com/login?return_to=%2FGraphify-Labs%2Fgraphify
Fork 7.8k https://github.com/login?return_to=%2FGraphify-Labs%2Fgraphify
Star 78.6k https://github.com/login?return_to=%2FGraphify-Labs%2Fgraphify
Code https://github.com/Graphify-Labs/graphify
Issues 197 https://github.com/Graphify-Labs/graphify/issues
Pull requests 232 https://github.com/Graphify-Labs/graphify/pulls
Discussions https://github.com/Graphify-Labs/graphify/discussions
Actions https://github.com/Graphify-Labs/graphify/actions
Projects https://github.com/Graphify-Labs/graphify/projects
Security and quality 0 https://github.com/Graphify-Labs/graphify/security
Insights https://github.com/Graphify-Labs/graphify/pulse
Code https://github.com/Graphify-Labs/graphify
Issues https://github.com/Graphify-Labs/graphify/issues
Pull requests https://github.com/Graphify-Labs/graphify/pulls
Discussions https://github.com/Graphify-Labs/graphify/discussions
Actions https://github.com/Graphify-Labs/graphify/actions
Projects https://github.com/Graphify-Labs/graphify/projects
Security and quality https://github.com/Graphify-Labs/graphify/security
Insights https://github.com/Graphify-Labs/graphify/pulse
yaanfpvhttps://github.com/yaanfpv
Graphify-Labs:v8https://github.com/Graphify-Labs/graphify/tree/v8
yaanfpv:feat/image-visionhttps://github.com/yaanfpv/graphify/tree/feat/image-vision
Conversationhttps://github.com/Graphify-Labs/graphify/pull/1110
Commits7 (7)https://github.com/Graphify-Labs/graphify/pull/1110/commits
Checkshttps://github.com/Graphify-Labs/graphify/pull/1110/checks
Files changedhttps://github.com/Graphify-Labs/graphify/pull/1110/files
feat(llm): stop reading images and PDFs as garbage in headless extracthttps://github.com/Graphify-Labs/graphify/pull/1110#top
yaanfpvhttps://github.com/yaanfpv
Graphify-Labs:v8https://github.com/Graphify-Labs/graphify/tree/v8
yaanfpv:feat/image-visionhttps://github.com/yaanfpv/graphify/tree/feat/image-vision
https://github.com/yaanfpv
yaanfpvhttps://github.com/yaanfpv
Jun 2, 2026https://github.com/Graphify-Labs/graphify/pull/1110#issue-4569227128
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
#1109https://github.com/Graphify-Labs/graphify/issues/1109
#450https://github.com/Graphify-Labs/graphify/issues/450
#181https://github.com/Graphify-Labs/graphify/issues/181
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
https://github.com/yaanfpv
feat(llm): see images in headless extract across all vision backendshttps://github.com/Graphify-Labs/graphify/pull/1110/commits/f462e777e158085be906cef9c11b9c04a5ec1a5c
f462e77https://github.com/Graphify-Labs/graphify/pull/1110/commits/f462e777e158085be906cef9c11b9c04a5ec1a5c
https://github.com/yaanfpv
yaanfpvhttps://github.com/yaanfpv
Jun 2, 2026 https://github.com/Graphify-Labs/graphify/pull/1110#ref-issue-4569221091
Headless graphify extract reads images as garbage text instead of seeing them #1109 https://github.com/Graphify-Labs/graphify/issues/1109
yaanfpvhttps://github.com/yaanfpv
June 2, 2026 12:38https://github.com/Graphify-Labs/graphify/pull/1110#commits-pushed-62a6785
https://github.com/yaanfpv
feat(llm): cap images per chunk so image-dense corpora stay within li…https://github.com/Graphify-Labs/graphify/pull/1110/commits/62a67856b705c3891d43836eca90569be368b63c
62a6785https://github.com/Graphify-Labs/graphify/pull/1110/commits/62a67856b705c3891d43836eca90569be368b63c
https://github.com/yaanfpv
feat(llm): extract PDF text in headless extract instead of raw byteshttps://github.com/Graphify-Labs/graphify/pull/1110/commits/b0473debe0a580c455ba606f9205ca0810ccd87e
b0473dehttps://github.com/Graphify-Labs/graphify/pull/1110/commits/b0473debe0a580c455ba606f9205ca0810ccd87e
https://github.com/yaanfpv
yaanfpvhttps://github.com/yaanfpv
Jun 2, 2026https://github.com/Graphify-Labs/graphify/pull/1110#event-26223834736
yaanfpvhttps://github.com/yaanfpv
June 2, 2026 12:46https://github.com/Graphify-Labs/graphify/pull/1110#commits-pushed-b02270f
https://github.com/yaanfpv
docs: note headless PDF text extractionhttps://github.com/Graphify-Labs/graphify/pull/1110/commits/b02270f5f028f000dc4160c0ae92670b0f9c8aa4
b02270fhttps://github.com/Graphify-Labs/graphify/pull/1110/commits/b02270f5f028f000dc4160c0ae92670b0f9c8aa4
https://github.com/yaanfpv
fix(llm): no per-image size cap for path-based backendshttps://github.com/Graphify-Labs/graphify/pull/1110/commits/18958a87697491e211a6c2f87ba4c8702848abc8
18958a8https://github.com/Graphify-Labs/graphify/pull/1110/commits/18958a87697491e211a6c2f87ba4c8702848abc8
https://github.com/safishamsi
safishamsihttps://github.com/safishamsi
Jun 2, 2026 https://github.com/Graphify-Labs/graphify/pull/1110#pullrequestreview-4407908363
View reviewed changes https://github.com/Graphify-Labs/graphify/pull/1110/files/18958a87697491e211a6c2f87ba4c8702848abc8
safishamsihttps://github.com/safishamsi
https://github.com/Graphify-Labs/graphify/pull/1110#pullrequestreview-4407908363
Learn morehttps://docs.github.com/articles/managing-disruptive-comments/#hiding-a-comment
@yaanfpvhttps://github.com/yaanfpv
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
https://github.com/yaanfpv
refactor(llm): pull the codex-cli backend out of this PRhttps://github.com/Graphify-Labs/graphify/pull/1110/commits/69b9758c84991b02200d950ae66a5c080b23f4ad
69b9758https://github.com/Graphify-Labs/graphify/pull/1110/commits/69b9758c84991b02200d950ae66a5c080b23f4ad
Graphify-Labs#1110https://github.com/Graphify-Labs/graphify/pull/1110
https://github.com/yaanfpv
yaanfpvhttps://github.com/yaanfpv
Jun 2, 2026https://github.com/Graphify-Labs/graphify/pull/1110#issuecomment-4601672546
@safishamsihttps://github.com/safishamsi
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
https://github.com/yaanfpv
yaanfpvhttps://github.com/yaanfpv
safishamsihttps://github.com/safishamsi
June 2, 2026 10:57https://github.com/Graphify-Labs/graphify/pull/1110#event-26233094917
https://github.com/yaanfpv
yaanfpvhttps://github.com/yaanfpv
Jun 2, 2026https://github.com/Graphify-Labs/graphify/pull/1110#issuecomment-4601767781
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
https://github.com/safishamsi
safishamsihttps://github.com/safishamsi
Jun 2, 2026https://github.com/Graphify-Labs/graphify/pull/1110#issuecomment-4604228813
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
https://github.com/yaanfpv
chore(llm): finish the codex-cli pull-out from the image/PDF PRhttps://github.com/Graphify-Labs/graphify/pull/1110/commits/25c0dcef605d6c0a04f5b34fcd0686fc63d5b3ab
25c0dcehttps://github.com/Graphify-Labs/graphify/pull/1110/commits/25c0dcef605d6c0a04f5b34fcd0686fc63d5b3ab
https://github.com/yaanfpv
yaanfpvhttps://github.com/yaanfpv
Jun 2, 2026https://github.com/Graphify-Labs/graphify/pull/1110#issuecomment-4604863992
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
https://github.com/yaanfpv
yaanfpvhttps://github.com/yaanfpv
Jun 6, 2026https://github.com/Graphify-Labs/graphify/pull/1110#issuecomment-4639732231
25c0dcehttps://github.com/Graphify-Labs/graphify/commit/25c0dcef605d6c0a04f5b34fcd0686fc63d5b3ab
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
safishamsihttps://github.com/safishamsi
Jun 7, 2026 https://github.com/Graphify-Labs/graphify/pull/1110#ref-commit-7467c1b
https://github.com/safishamsi
https://github.com/claude
feat/fix: land PRshttps://github.com/Graphify-Labs/graphify/commit/7467c1b6a41505495a5a0adea430431759aef8d6
#1118https://github.com/Graphify-Labs/graphify/pull/1118
#1110https://github.com/Graphify-Labs/graphify/pull/1110
#1159https://github.com/Graphify-Labs/graphify/pull/1159
#1107https://github.com/Graphify-Labs/graphify/pull/1107
#1103https://github.com/Graphify-Labs/graphify/pull/1103
(graph quality + new…https://github.com/Graphify-Labs/graphify/commit/7467c1b6a41505495a5a0adea430431759aef8d6
7467c1bhttps://github.com/Graphify-Labs/graphify/commit/7467c1b6a41505495a5a0adea430431759aef8d6
#1118https://github.com/Graphify-Labs/graphify/pull/1118
#1116https://github.com/Graphify-Labs/graphify/issues/1116
#1110https://github.com/Graphify-Labs/graphify/pull/1110
#1159https://github.com/Graphify-Labs/graphify/pull/1159
#1107https://github.com/Graphify-Labs/graphify/pull/1107
#1103https://github.com/Graphify-Labs/graphify/pull/1103
#1112https://github.com/Graphify-Labs/graphify/issues/1112
https://github.com/safishamsi
safishamsihttps://github.com/safishamsi
Jun 7, 2026https://github.com/Graphify-Labs/graphify/pull/1110#issuecomment-4640901720
7467c1bhttps://github.com/Graphify-Labs/graphify/commit/7467c1b6a41505495a5a0adea430431759aef8d6
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
https://github.com/safishamsi
safishamsihttps://github.com/safishamsi
Jun 7, 2026https://github.com/Graphify-Labs/graphify/pull/1110#event-26431291138
https://github.co/hiddenchars
https://github.com/Graphify-Labs/graphify/pull/{{ revealButtonHref }}
Sign up for freehttps://github.com/join?source=comment-repo
Sign in to commenthttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FGraphify-Labs%2Fgraphify%2Fpull%2F1110
https://github.com/safishamsi
safishamsi https://github.com/safishamsi
Headless graphify extract reads images as garbage text instead of seeing them https://github.com/Graphify-Labs/graphify/issues/1109
Please reload this pagehttps://github.com/Graphify-Labs/graphify/pull/1110
https://github.com/yaanfpv
https://github.com/safishamsi
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.