{"schema_version":"onlylabs.public_signal.v1","title":"DeepInfra Repo: deepinfra/ocr-tools","description":"DeepInfra repo signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/9ebf8231-3e8b-45f3-bf84-87e5ccc84ddb","json_url":"https://onlylabs.fyi/signals/9ebf8231-3e8b-45f3-bf84-87e5ccc84ddb/signal.json","generated_at":"2026-06-11T04:09:59.494597+00:00","org":{"slug":"deepinfra","name":"DeepInfra","category":"neocloud","category_label":"Neocloud","dossier_url":"https://onlylabs.fyi/labs/deepinfra","dossier_json_url":"https://onlylabs.fyi/labs/deepinfra/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/9ebf8231-3e8b-45f3-bf84-87e5ccc84ddb","signal_json":"https://onlylabs.fyi/signals/9ebf8231-3e8b-45f3-bf84-87e5ccc84ddb/signal.json","source":"https://github.com/deepinfra/ocr-tools","lab_dossier":"https://onlylabs.fyi/labs/deepinfra","lab_dossier_json":"https://onlylabs.fyi/labs/deepinfra/dossier.json","analysis":"https://onlylabs.fyi/analysis/deepinfra","analysis_json":"https://onlylabs.fyi/analysis/deepinfra/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/deepinfra/evidence.json","category":"https://onlylabs.fyi/neoclouds","category_json":"https://onlylabs.fyi/neoclouds.json","category_feed":"https://onlylabs.fyi/neoclouds/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","topic":null,"topic_signals_json":null,"topic_feed":null,"data_business":null},"answer_pack":{"answer":"DeepInfra published deepinfra/ocr-tools (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo deepinfra/ocr-tools · language Python · New repo, low traction. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","signal_desk":"repos","source_context":{"source_url":"https://github.com/deepinfra/ocr-tools","source_host":"github.com","occurred_at":"2025-08-02T22:31:20+00:00","first_seen_at":"2026-06-05T22:32:12.181599+00:00","date_source":"source","context":"Python"},"context_markers":[{"label":"Lab","value":"DeepInfra","source":"signal"},{"label":"Signal desk","value":"repos","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"deepinfra/ocr-tools","source":"source"},{"label":"Language","value":"Python","source":"source"},{"label":"Stars","value":"5","source":"traction"},{"label":"Notability","value":"New repo, low traction","source":"signal"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/deepinfra/ocr-tools"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T04:09:59.494597+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/9ebf8231-3e8b-45f3-bf84-87e5ccc84ddb/signal.json","dossier_json":"https://onlylabs.fyi/labs/deepinfra/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/deepinfra/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/deepinfra/evidence.json","topic_signals_json":null,"topic_feed":null,"category_signals_json":"https://onlylabs.fyi/signals.json?category=neocloud","data_radar_json":null,"opportunities_json":null},"analysis_playbook":{"objective":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","evidence_focus":["repo name","owner","description","language","stars","source URL","first seen time","data, eval, infra, safety, and product terms"],"extraction_questions":["What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Is the repo new evidence for a lab direction that is not yet in writing or releases?","Which related signals should an analyst inspect next?"],"signal_questions":["What does this new repository reveal before a formal announcement exists?","What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Do the 6 related repo signals show a repeated pattern?"],"output_fields":["org","repo","technical_theme","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, interpret the repository as source-grounded category strategy evidence.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/9ebf8231-3e8b-45f3-bf84-87e5ccc84ddb/signal.json","required":true},{"label":"source","url":"https://github.com/deepinfra/ocr-tools","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/deepinfra/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/deepinfra/evidence.json","required":true},{"label":"topic_signals_json","url":null,"required":false},{"label":"data_radar_json","url":null,"required":false}],"expected_output":["one-paragraph source-grounded interpretation","category-specific implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze DeepInfra's repo signal \"deepinfra/ocr-tools\" for neocloud strategy."},"semantic_triples":[{"subject":"DeepInfra","predicate":"published repo","object":"deepinfra/ocr-tools","text":"DeepInfra published repo deepinfra/ocr-tools."},{"subject":"deepinfra/ocr-tools","predicate":"is classified as","object":"repo signal","text":"deepinfra/ocr-tools is classified as repo signal."},{"subject":"deepinfra/ocr-tools","predicate":"belongs to","object":"repos desk","text":"deepinfra/ocr-tools belongs to repos desk."},{"subject":"deepinfra/ocr-tools","predicate":"has context","object":"Python","text":"deepinfra/ocr-tools has context Python."},{"subject":"deepinfra/ocr-tools","predicate":"has evidence coverage","object":"1 captured evidence page","text":"deepinfra/ocr-tools has evidence coverage 1 captured evidence page."},{"subject":"deepinfra/ocr-tools","predicate":"has captured page count","object":"1","text":"deepinfra/ocr-tools has captured page count 1."},{"subject":"deepinfra/ocr-tools","predicate":"has readable page count","object":"1","text":"deepinfra/ocr-tools has readable page count 1."},{"subject":"deepinfra/ocr-tools","predicate":"has related signal count","object":"6","text":"deepinfra/ocr-tools has related signal count 6."},{"subject":"deepinfra/ocr-tools","predicate":"has analysis playbook objective","object":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","text":"deepinfra/ocr-tools has analysis playbook objective Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.."},{"subject":"deepinfra/ocr-tools","predicate":"has source host","object":"github.com","text":"deepinfra/ocr-tools has source host github.com."},{"subject":"deepinfra/ocr-tools","predicate":"has lab","object":"DeepInfra","text":"deepinfra/ocr-tools has lab DeepInfra."},{"subject":"deepinfra/ocr-tools","predicate":"has signal desk","object":"repos","text":"deepinfra/ocr-tools has signal desk repos."},{"subject":"deepinfra/ocr-tools","predicate":"has source host","object":"github.com","text":"deepinfra/ocr-tools has source host github.com."},{"subject":"deepinfra/ocr-tools","predicate":"has repository","object":"deepinfra/ocr-tools","text":"deepinfra/ocr-tools has repository deepinfra/ocr-tools."},{"subject":"deepinfra/ocr-tools","predicate":"has language","object":"Python","text":"deepinfra/ocr-tools has language Python."},{"subject":"deepinfra/ocr-tools","predicate":"has stars","object":"5","text":"deepinfra/ocr-tools has stars 5."},{"subject":"deepinfra/ocr-tools","predicate":"has notability","object":"New repo, low traction","text":"deepinfra/ocr-tools has notability New repo, low traction."}]},"intelligence":{"signal_desk":"repos","answer":"DeepInfra published deepinfra/ocr-tools (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo deepinfra/ocr-tools · language Python · New repo, low traction. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","semantic_triples":[{"subject":"DeepInfra","predicate":"published repo","object":"deepinfra/ocr-tools","text":"DeepInfra published repo deepinfra/ocr-tools."},{"subject":"deepinfra/ocr-tools","predicate":"is classified as","object":"repo signal","text":"deepinfra/ocr-tools is classified as repo signal."},{"subject":"deepinfra/ocr-tools","predicate":"belongs to","object":"repos desk","text":"deepinfra/ocr-tools belongs to repos desk."},{"subject":"deepinfra/ocr-tools","predicate":"has context","object":"Python","text":"deepinfra/ocr-tools has context Python."},{"subject":"deepinfra/ocr-tools","predicate":"has evidence coverage","object":"1 captured evidence page","text":"deepinfra/ocr-tools has evidence coverage 1 captured evidence page."}]},"signal":{"id":"9ebf8231-3e8b-45f3-bf84-87e5ccc84ddb","url":"https://onlylabs.fyi/signals/9ebf8231-3e8b-45f3-bf84-87e5ccc84ddb","json_url":"https://onlylabs.fyi/signals/9ebf8231-3e8b-45f3-bf84-87e5ccc84ddb/signal.json","source_url":"https://github.com/deepinfra/ocr-tools","title":"deepinfra/ocr-tools","summary":"DeepInfra published a new repository. onlylabs watches repos for tooling, eval, infra, and model-adjacent work.","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"deepinfra","name":"DeepInfra","category":"neocloud"},"occurred_at":"2025-08-02T22:31:20+00:00","first_seen_at":"2026-06-05T22:32:12.181599+00:00","date_source":"source","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/deepinfra/ocr-tools"]},"facets":{"repo":"deepinfra/ocr-tools","language":"Python"},"traction":{"github_stars":5,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":null},"primary_evidence_page":{"url":"https://github.com/deepinfra/ocr-tools","final_url":"https://github.com/deepinfra/ocr-tools","title":"deepinfra/ocr-tools repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T04:09:59.494597+00:00","bytes":7657,"raw_path":"a913a1e3e001964a37bd8279060b59d6b2d160bf0ef552abf62a05685868210e.json","content_hash":"afe043f8ac0792f84387cf74aa7904abfc557c9978901c41d316f928ae425d08","excerpt_chars":1200,"truncated":false,"excerpt":"deepinfra/ocr-tools Language: Python Stars: 5 Forks: 2 Open issues: 1 Created: 2025-08-02T22:31:20Z Pushed: 2025-08-02T23:13:51Z Default branch: main Fork: no Archived: no README: ocr-tools This document is tutorial how to use olmocr endpoint on DeepInfra to parse texts from pdf Install requirements pip install -r requirements.txt (if linux): sudo apt-get install poppler-utils (if macOS): brew install poppler Run command python3 scrape_pdf.py --model allenai/olmOCR-7B-0725-FP8 --api-key DEEPINFRA_API_KEY --pdf-path horribleocr.pdf"},"evidence_pages":[{"url":"https://github.com/deepinfra/ocr-tools","final_url":"https://github.com/deepinfra/ocr-tools","title":"deepinfra/ocr-tools repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T04:09:59.494597+00:00","bytes":7657,"raw_path":"a913a1e3e001964a37bd8279060b59d6b2d160bf0ef552abf62a05685868210e.json","content_hash":"afe043f8ac0792f84387cf74aa7904abfc557c9978901c41d316f928ae425d08","excerpt_chars":1200,"truncated":false,"excerpt":"deepinfra/ocr-tools Language: Python Stars: 5 Forks: 2 Open issues: 1 Created: 2025-08-02T22:31:20Z Pushed: 2025-08-02T23:13:51Z Default branch: main Fork: no Archived: no README: ocr-tools This document is tutorial how to use olmocr endpoint on DeepInfra to parse texts from pdf Install requirements pip install -r requirements.txt (if linux): sudo apt-get install poppler-utils (if macOS): brew install poppler Run command python3 scrape_pdf.py --model allenai/olmOCR-7B-0725-FP8 --api-key DEEPINFRA_API_KEY --pdf-path horribleocr.pdf"}],"related_signals":[{"id":"5df404e9-e2d4-4772-ae7b-0b2d29bc0842","url":"https://onlylabs.fyi/signals/5df404e9-e2d4-4772-ae7b-0b2d29bc0842","source_url":"https://github.com/deepinfra/cookbooks","title":"deepinfra/cookbooks","context":"Jupyter Notebook","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"deepinfra","name":"DeepInfra","category":"neocloud"},"occurred_at":"2025-12-15T01:25:49+00:00","first_seen_at":"2026-06-05T22:32:12.181599+00:00","date_source":"source"},{"id":"a6e60628-e892-4e9e-a5c8-24ca20271c02","url":"https://onlylabs.fyi/signals/a6e60628-e892-4e9e-a5c8-24ca20271c02","source_url":"https://github.com/deepinfra/docs","title":"deepinfra/docs","context":"MDX","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"deepinfra","name":"DeepInfra","category":"neocloud"},"occurred_at":"2025-11-17T23:21:43+00:00","first_seen_at":"2026-06-05T22:32:12.181599+00:00","date_source":"source"},{"id":"08f87401-9139-437b-917f-140af4469f60","url":"https://onlylabs.fyi/signals/08f87401-9139-437b-917f-140af4469f60","source_url":"https://github.com/deepinfra/deepinfra-chat","title":"deepinfra/deepinfra-chat","context":"TypeScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"deepinfra","name":"DeepInfra","category":"neocloud"},"occurred_at":"2025-03-17T09:01:46+00:00","first_seen_at":"2026-06-05T22:32:12.181599+00:00","date_source":"source"},{"id":"e93a56e2-ff1b-4328-959d-dd07c0cec495","url":"https://onlylabs.fyi/signals/e93a56e2-ff1b-4328-959d-dd07c0cec495","source_url":"https://github.com/deepinfra/deepinfra-node","title":"deepinfra/deepinfra-node","context":"TypeScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"deepinfra","name":"DeepInfra","category":"neocloud"},"occurred_at":"2024-03-12T22:26:38+00:00","first_seen_at":"2026-06-05T22:32:12.181599+00:00","date_source":"source"},{"id":"ad075988-5f67-4aaa-8fc2-841677e49a66","url":"https://onlylabs.fyi/signals/ad075988-5f67-4aaa-8fc2-841677e49a66","source_url":"https://github.com/deepinfra/cog-llama-2","title":"deepinfra/cog-llama-2","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"deepinfra","name":"DeepInfra","category":"neocloud"},"occurred_at":"2023-08-01T09:33:38+00:00","first_seen_at":"2026-06-05T22:32:12.181599+00:00","date_source":"source"},{"id":"f7426dd2-4984-4153-8ec0-d25d0931be3d","url":"https://onlylabs.fyi/signals/f7426dd2-4984-4153-8ec0-d25d0931be3d","source_url":"https://github.com/deepinfra/deepctl","title":"deepinfra/deepctl","context":"Rust","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"deepinfra","name":"DeepInfra","category":"neocloud"},"occurred_at":"2022-12-07T22:25:03+00:00","first_seen_at":"2026-06-05T22:32:12.181599+00:00","date_source":"source"}]}