home.social

#docling — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #docling, aggregated by home.social.

fetched live
  1. I'm ex[experimenting with #docling
    nice, ran it on a pdf the markdown output was 10 times the original size and it took only over one hours of intense compute

    guess adapting my procedures not necessary 😊

  2. I'm ex[experimenting with #docling
    nice, ran it on a pdf the markdown output was 10 times the original size and it took only over one hours of intense compute

    guess adapting my procedures not necessary 😊

  3. Join Ming and I for a #Docling workshop at @pycon_austria this weekend! It's a free event with a wide range of talks, hands-on workshops, and networking opportunities.

    "Workshop: Learn to Unlock Document Intelligence with Open-Source AI" will be on Sunday, April 19, at 10:00-12:00 in room E.HG 209. More details including venue & registration: 2026.pycon.at/

    #PyCon #PyConAT #PyConAT26 #opensource

  4. Join Ming and I for a #Docling workshop at @pycon_austria this weekend! It's a free event with a wide range of talks, hands-on workshops, and networking opportunities.

    "Workshop: Learn to Unlock Document Intelligence with Open-Source AI" will be on Sunday, April 19, at 10:00-12:00 in room E.HG 209. More details including venue & registration: 2026.pycon.at/

    #PyCon #PyConAT #PyConAT26 #opensource

  5. Here's the presentation @philnash and I gave at #OpenSearchCon China about integrating #Docling with OpenSearch for advanced RAG: youtube.com/watch?v=IqUJVGyI5to

    Our slides are available on sessionize: opensearchcon-china-2026.sessi

    Thanks to @OpenSearchProject, @krisfreedain for having us in #Shanghai!

  6. Here's the presentation @philnash and I gave at #OpenSearchCon China about integrating #Docling with OpenSearch for advanced RAG: youtube.com/watch?v=IqUJVGyI5to

    Our slides are available on sessionize: opensearchcon-china-2026.sessi

    Thanks to @OpenSearchProject, @krisfreedain for having us in #Shanghai!

  7. Are you going to KubeCon EU? Come find me and get one of these awesome (limited in number) Duckling stickers. #duckling #kubeconeu #docling twp.ai/E6HlHZ

  8. Are you going to KubeCon EU? Come find me and get one of these awesome (limited in number) Duckling stickers. #duckling #kubeconeu #docling twp.ai/E6HlHZ

  9. Contrary to what I'm reading, #Claude is far worse than I remember. It often doesn't fully understand simple questions and needs nudging - and as in this case, can't solve even trivial problems which only require careful reading of the log.

    It took #Kimi 10secs to solve a problem with an api call to a #docling
    server crashing when accessed over its api. I used Kimi in the browser. #ClaudeCode Sonnet 4.6 had full access to the actual server and couldn't solve the issue after 30 mins of repeated attempts.

    ```
    The root cause is clear: **Docling workers are crashing due to missing EasyOCR dependency**, causing the async jobs to fail. OpenWebUI polls for results, gets a 404 because the job died, and reports "Task result not found."

    **Fix the Docling installation:**

    ```bash
    # Stop the service
    sudo launchctl unload /Library/LaunchDaemons/com.docling-serve.plist

    # Install EasyOCR in the correct uv tool environment
    uv tool install --upgrade docling-serve --with easyocr

    # Or if that doesn't work, run the specific Python interpreter:
    /Users/urisharf/.local/share/uv/tools/docling-serve/bin/python -m pip install easyocr

    # Reload
    sudo launchctl load /Library/LaunchDaemons/com.docling-serve.plist
    ```

    **Alternative (if you don't need OCR):** Configure Docling to use a different OCR engine or disable it. Check Docling's env vars for `DOCLING_OCR_ENGINE` or similar.

    **Verify the fix:**
    ```bash
    curl -X POST http://mbp.lan:5001/v1/convert/source \
    -H "Content-Type: application/json" \
    -d '{"source": "arxiv.org/pdf/2206.01062.pdf"}'
    ```

    The duplicate `libavdevice` dylibs warning is harmless noise from Gradio/CV2 conflicts, but the EasyOCR error is fatal.
    ```

    #AIHype #TheAICON #Anthropic

  10. Contrary to what I'm reading, #Claude is far worse than I remember. It often doesn't fully understand simple questions and needs nudging - and as in this case, can't solve even trivial problems which only require careful reading of the log.

    It took #Kimi 10secs to solve a problem with an api call to a #docling
    server crashing when accessed over its api. I used Kimi in the browser. #ClaudeCode Sonnet 4.6 had full access to the actual server and couldn't solve the issue after 30 mins of repeated attempts.

    ```
    The root cause is clear: **Docling workers are crashing due to missing EasyOCR dependency**, causing the async jobs to fail. OpenWebUI polls for results, gets a 404 because the job died, and reports "Task result not found."

    **Fix the Docling installation:**

    ```bash
    # Stop the service
    sudo launchctl unload /Library/LaunchDaemons/com.docling-serve.plist

    # Install EasyOCR in the correct uv tool environment
    uv tool install --upgrade docling-serve --with easyocr

    # Or if that doesn't work, run the specific Python interpreter:
    /Users/urisharf/.local/share/uv/tools/docling-serve/bin/python -m pip install easyocr

    # Reload
    sudo launchctl load /Library/LaunchDaemons/com.docling-serve.plist
    ```

    **Alternative (if you don't need OCR):** Configure Docling to use a different OCR engine or disable it. Check Docling's env vars for `DOCLING_OCR_ENGINE` or similar.

    **Verify the fix:**
    ```bash
    curl -X POST http://mbp.lan:5001/v1/convert/source \
    -H "Content-Type: application/json" \
    -d '{"source": "arxiv.org/pdf/2206.01062.pdf"}'
    ```

    The duplicate `libavdevice` dylibs warning is harmless noise from Gradio/CV2 conflicts, but the EasyOCR error is fatal.
    ```

    #AIHype #TheAICON #Anthropic

  11. @karstenpe ich habe jetzt zwei Varianten der Notizbücher vom Remarkable lokal gespeichert: 1x als PDF mit Bitmap drin und 1x PDF mit Vektoren.

    Welches CLI-Tool würdest du mir für #OCR empfehlen? #Tesseract?

    Bei der Gelegenheit werde ich auch mal #Docling mit OCR-Option ausprobieren, das hat aber glaube ich keine eigene Engine.

    Geht das auch mit #Ollama direkt aus PDF und einem lokalen LLM? Hat jemand Ideen?

  12. @karstenpe ich habe jetzt zwei Varianten der Notizbücher vom Remarkable lokal gespeichert: 1x als PDF mit Bitmap drin und 1x PDF mit Vektoren.

    Welches CLI-Tool würdest du mir für #OCR empfehlen? #Tesseract?

    Bei der Gelegenheit werde ich auch mal #Docling mit OCR-Option ausprobieren, das hat aber glaube ich keine eigene Engine.

    Geht das auch mit #Ollama direkt aus PDF und einem lokalen LLM? Hat jemand Ideen?

  13. Tomorrow (Feb 4) at #CfgMgmtCamp in Ghent, Ming and I will run a workshop on #Docling at 14:00 in B.1.031 - cfp.cfgmgmtcamp.org/ghent2026/

    Join us! @cfgmgmtcamp

  14. Tomorrow (Feb 4) at #CfgMgmtCamp in Ghent, Ming and I will run a workshop on #Docling at 14:00 in B.1.031 - cfp.cfgmgmtcamp.org/ghent2026/

    Join us! @cfgmgmtcamp

  15. The slides and recording for my presentation on Get your docs in a row with #Docling are now available - fosdem.org/2026/schedule/event

    Thanks to @fosdem organizers and volunteers for another amazing event. My 11th in-person #FOSDEM (13 including virtual ones).

  16. The slides and recording for my presentation on Get your docs in a row with #Docling are now available - fosdem.org/2026/schedule/event

    Thanks to @fosdem organizers and volunteers for another amazing event. My 11th in-person #FOSDEM (13 including virtual ones).

  17. The docling-testcontainers module provides a ready-to-use Testcontainers integration for running a Docling Serve instance, wrapping the official container image and exposing a simple Java API.
    testcontainers.com/modules/doc

    #Docling #Java #Testcontainers

  18. The docling-testcontainers module provides a ready-to-use Testcontainers integration for running a Docling Serve instance, wrapping the official container image and exposing a simple Java API.
    testcontainers.com/modules/doc

    #Docling #Java #Testcontainers

  19. Как затащить AI в Java/Kotlin проект

    Мир Enterprise-разработки на Java/Kotlin и мир нейронных сетей кажутся параллельными вселенными. С одной стороны - статическая типизация, многопоточность, Spring-контейнеры, а с другой - Python-скрипты, тензорные операции и эксперименты в Jupyter Notebook. Между ними - пропасть, через которую многие команды не решаются перешагнуть. Однако необходимость строить этот мост возникает всё чаще. Заказчик хочет «искусственный интеллект» в новом фиче, аналитики мечтают о реализации чат-бота с преферансом и барышнями, а менеджеры слышали, что конкуренты уже всё автоматизировали. Как же совместить надежность и структуру JVM-проекта с гибкостью и мощью AI? В этой статье постараемся разобраться какие инструменты для этого есть на данный момент и как с ними работать.

    habr.com/ru/articles/984544/

    #AI #ИИ #Java #Kotlin #LLM #State_Graph #Vector_DB #Docling #Embeddings

  20. Just published a new deep-dive on building enterprise-grade RAG in Java.

    In this tutorial, we combine:

    • Quarkus
    • Docling (layout-aware PDF parsing)
    • pgvector + PostgreSQL
    • Local LLMs via Ollama
    • And a simple guardrail layer

    This is the most complete RAG pipeline I’ve built so far, and it’s fully open for you to copy, run, and adapt.

    Read here:
    the-main-thread.com/p/enterpri

    #Java #Quarkus #LLM #RAG #Docling #OpenSource

  21. Just published a new deep-dive on building enterprise-grade RAG in Java.

    In this tutorial, we combine:

    • Quarkus
    • Docling (layout-aware PDF parsing)
    • pgvector + PostgreSQL
    • Local LLMs via Ollama
    • And a simple guardrail layer

    This is the most complete RAG pipeline I’ve built so far, and it’s fully open for you to copy, run, and adapt.

    Read here:
    the-main-thread.com/p/enterpri

    #Java #Quarkus #LLM #RAG #Docling #OpenSource

  22. In this new article, I describe how to build a Retrieval Augmented Generation system in Java using Spring AI and Docling for advanced, privacy-focused document processing. You'll learn how to design an Ingestion Pipeline powered by Docling for loading, converting, and chunking any type of document for your RAG use cases.

    #SpringAI #Docling #Arconia #Java

    thomasvitale.com/rag-docling-j

  23. In this new article, I describe how to build a Retrieval Augmented Generation system in Java using Spring AI and Docling for advanced, privacy-focused document processing. You'll learn how to design an Ingestion Pipeline powered by Docling for loading, converting, and chunking any type of document for your RAG use cases.

    #SpringAI #Docling #Arconia #Java

    thomasvitale.com/rag-docling-j

  24. Docling is an open-source, privacy-focused solution for advanced document parsing. Using the brand-new Docling Java SDK and Arconia, I'll show you how to integrate Docling into your Spring Boot applications, and prepare documents for RAG and GenAI.

    #Java #SpringBoot #AI #Docling

    thomasvitale.com/ai-document-p

  25. Docling is an open-source, privacy-focused solution for advanced document parsing. Using the brand-new Docling Java SDK and Arconia, I'll show you how to integrate Docling into your Spring Boot applications, and prepare documents for RAG and GenAI.

    #Java #SpringBoot #AI #Docling

    thomasvitale.com/ai-document-p

  26. Docling #Java is the official Java client and tooling for #Docling — a suite that simplifies document processing and parsing across diverse formats (with advanced PDF understanding) and integrates seamlessly with #GenAI frameworks.
    docling-project.github.io/docl

  27. Docling #Java is the official Java client and tooling for #Docling — a suite that simplifies document processing and parsing across diverse formats (with advanced PDF understanding) and integrates seamlessly with #GenAI frameworks.
    docling-project.github.io/docl

  28. @Semtex Noch nicht, kann ich aber mal in ein Gist schmeißen. Ist aktuell "nur" ein Pythonskript, will aber auch noch ein n8n-Workflow dazu bauen. Vorher will ich aber noch #Marker als Alternative zu #Docling probieren.

  29. @Semtex Noch nicht, kann ich aber mal in ein Gist schmeißen. Ist aktuell "nur" ein Pythonskript, will aber auch noch ein n8n-Workflow dazu bauen. Vorher will ich aber noch #Marker als Alternative zu #Docling probieren.

  30. Habe mir heute im Rahmen meiner #pke25 Lernaktivitäten mal eine #Docling Pipeline aufgesetzt, um meine ganzen PDF-Sammlungen für die Nutzung mit KI vorzubereiten (Bücher, Artikel, Studien, Präsentationen etc.). Eine Seite braucht knapp eine Sekunde.

  31. Habe mir heute im Rahmen meiner #pke25 Lernaktivitäten mal eine #Docling Pipeline aufgesetzt, um meine ganzen PDF-Sammlungen für die Nutzung mit KI vorzubereiten (Bücher, Artikel, Studien, Präsentationen etc.). Eine Seite braucht knapp eine Sekunde.

  32. We've seen using #docling a lot at work lately to parse all kinds of documents in various formats. It's handy for converting them into a common JSON document.

    major.io/p/fun-with-docling/

    #rag #ai #knowledge #documents

  33. We've seen using #docling a lot at work lately to parse all kinds of documents in various formats. It's handy for converting them into a common JSON document.

    major.io/p/fun-with-docling/

    #rag #ai #knowledge #documents

  34. Wow, #docling added support for Arabic and can handle complex documents with text that goes right to left!

    #devconf_us #devconfus #ai #rag

  35. Wow, #docling added support for Arabic and can handle complex documents with text that goes right to left!

    #devconf_us #devconfus #ai #rag

  36. Context is important! Vegetative electron microscopy does not exist! 😂

    Another reason to use Docling for your documents. RAG is another garbage in, garbage out situation.

    #devconf_us #devconf #ai #docling