Head of Engineering

PDF to Markdown: what LiteParse's September 2026 update changes. LiteParse 2.14.6 cuts PDF text extraction by 20-25%, lifts table accuracy on all three benchmarks, and adds block-level visual grounding plus an is-complex router. What the vendor-reported numbers say - and how to choose a PDF to Markdown approach. Markdown documentation tool Sep 23, 2026 URL to Any On September 22, LlamaIndex shipped a major update to LiteParse - its model-free, open-source PDF parser that launched earlier this year - and it directly changes the math for anyone converting PDFs to Markdown. Version 2.14.6 cuts 20-25% off the time PDFium spends extracting text, lifts table accuracy on all three of the project's benchmarks, adds block-level visual grounding, and introduces an is-complex API that flags hard documents before you parse them. With text extraction now averaging 2.8 ms per page and full markdown rendering 3.9 ms per page (OCR off), the local open-source parser is no longer the slow option - and the release is unusually candid about where it still hits a ceiling. Key takeaways. * LiteParse 2.14.6 extracts text about 20-25% faster than 2.1, after surgery on the project's PDFium fork. Vendor-measured: 2.76 ms/page versus 3.51, with pypdf at 35.78 on the same document set. * Full markdown rendering runs at 3.94 ms/page in the same benchmark - 1.5x faster than the next tool listed and over 35x faster than pymupdf4llm or markitdown. * Table extraction improved on all three benchmarks; table-structure (TEDS) rose from 0.693 to 0.818 on opendataloader-bench. * Markdown elements can now be exported as blocks with bounding boxes, so each piece of output traces back to a region of the original page. * A new is-complex API (~3.5 ms/page) tells you when a document needs a stronger, model-based pipeline instead. The PDFium surgery behind the 20-25% speedup. LiteParse is a model-free parser: it gets its speed from PDFium, Google's PDF library, which the team maintains as its own fork. That ownership is what made this update possible. Profiling showed that two functions - FPDF_LoadPage and FPDFText_LoadPage - accounted for over half of total runtime, and that this time was dominated by huge numbers of tiny memory allocations. The fix that stands out is allocator-level: the team vendored mimalloc directly into the fork, but only replaced PDFium's own allocation funnels. libc malloc is untouched, which matters if you embed LiteParse in a Node or Python process - your host process keeps its own allocator, and only the parsing engine gets the faster one. Alongside that: caching and memoization on hot paths like font widths and charcodes, a fix for quadratic complexity in space collapsing, and eager memory release on lists. The measured result, on LlamaIndex's set of real-world PDFs with OCR off: Try Productivity Apps | Tool | ms/page (text extraction) | | LiteParse 2.14.6 | 2.76 | | LiteParse 2.1 | 3.51 | | pypdf | 35.78 | For full markdown rendering, the gap against other converters is wider: | Tool | ms/page (markdown) | vs LiteParse | | LiteParse 2.14.6 | 3.94 | 1.0x | | pdf-inspector 1.19 | 5.72 | 1.5x | | opendataloader-pdf 2.5.7 | 24.15 | 6.1x | | pymupdf4llm 1.28.2 | 140.80 | 35.7x | | markitdown 0.1.7 | 191.07 | 48.5x | One honest note from the post itself: markdown accuracy improvements added some latency since 2.1, and the PDFium work won that time back. The rendering speedup is not free - it is net of heavier heuristics. Table accuracy rose on all three benchmarks. Speed alone would be a shallow update. The release also reports accuracy gains across every benchmark LiteParse tracks, all measured with OCR off: * opendataloader-bench (200 documents): table structure (TEDS) climbed from 0.693 in 2.1 to 0.818 in 2.14.6, and overall from 0.875 to 0.886. Notably, that TEDS figure now leads the commercial engine in the comparison (nutrient, at 0.708), though nutrient still leads on reading order (NID 0.925 versus 0.917) - so this is progress, not a sweep. * olmOCR-bench (1,403 pages): table tests improved from 48.2 to 52.5, and overall from 39.1 to 39.6. * ParseBench (2,049 documents): overall 0.364, with the visual-grounding score more than doubling (0.108 to 0.297). ParseBench changed scorers since the previous post, so the team re-ran 2.1 under the current harness rather than quoting the old number against a new ruler - the right way to do it. Under the hood, the accuracy work targeted drawn rule-lines, column detection, multi-line table headers, and right-to-left versus left-to-right handling in multilingual documents. Latency offsets came from bounding-box extraction fixes, better overlap detection on dense pages, and clamping page-screenshot sizes. Visual grounding: markdown you can trace back to the page. Until now, LiteParse emitted a markdown string and you took it or left it. The update adds an option to export the underlying block structure instead: each markdown element (paragraph, heading, and so on) comes back as an object with its text, its level where relevant, and a bounding box in page coordinates. That changes what you can build downstream. A RAG pipeline can cite which region of which page an answer came from. A QA workflow can highlight extracted headings against the original scan and spot misreads. Document-search products can jump users from a markdown snippet to the exact spot on the page. Grounding turns the parser's output from a text blob into an addressable structure. The third addition, is-complex, costs about 3.5 ms per page and reports whether a document will stress a model-free parser: scanned pages, garbled fonts or text, text coverage, and layout signals like likely tables or multi-column text, detected with the same heuristics the markdown renderer uses. The useful framing comes from LlamaIndex itself: a model-free parser "can never beat more advanced parsing pipelines" on complex documents, because there is no model in the loop to reason about a messy layout. is-complex exists so you do not have to find that out the hard way - run the cheap check first, route flagged documents to a stronger pipeline (LlamaParse is the suggested escalation), and fast-path the rest. The complexity guide documents the full output shape. Choosing your PDF to Markdown approach. The update reshuffles the decision more than it settles it. Match the approach to the job: * Batch or embedded conversion, text-native PDFs. Local open-source parsing is now the default candidate. LiteParse 2.14.6 gives you millisecond-per-page extraction, runs in Node, Python, Rust, and even the browser via WASM, and ships under Apache-2.0. If your documents are digital-native (not scans), the heuristic accuracy gains make the markdown usable without a model in the loop. * Complex layouts, scans, high-stakes tables. Use is-complex to detect them, then route to a model-based pipeline. Faster heuristics do not change the ceiling on documents that need reasoning - that is a different tool category. * One-off files, no install. Online converters remain fine for occasional single documents; you trade pipeline control for convenience. * And check the source before parsing at all. A surprising number of "PDFs" are just printed web pages. If your content lives at a URL, converting the page directly is faster and cleaner than parsing a PDF rendering of it - URL to Any's URL to Markdown tool turns any public page into clean Markdown in the browser, free and without signup, and it never touches your local files. Limits worth knowing. Every number in this article is vendor-reported: LlamaIndex's own benchmarks, its document sets, with OCR off (turning OCR on adds modest gains, especially with PaddleOCR). "Fastest" is the post's own claim, scoped to open parsers it has tested. The adoption figures - 300k+ weekly downloads, 12k+ GitHub stars - are also from the announcement. And the heuristic ceiling is real, by the vendor's own statement; this update moves the speed line and the table-accuracy line, not the complexity ceiling. The takeaway. LiteParse 2.14.6 makes local PDF-to-Markdown conversion roughly 20-25% faster where it was already fastest, gains real ground on table accuracy, and adds the two things practitioners actually ask of a parser: proof of where output came from, and an early warning of when to escalate. If PDF parsing has been the slow, unreliable step in your document pipeline, the September update is a concrete reason to re-run your own documents through it - and to route around it, deliberately, when is-complex says so.

Implementing RAG with Qdrant and LlamaIndex for Production LLM Applications. The landscape of Artificial Intelligence is rapidly evolving, and Large Language Models (LLMs) are at the forefront of this transformation. While LLMs offer incredible capabilities, deploying them effectively in production environments for real-world applications presents unique challenges. One of the most significant hurdles is ensuring that LLMs can access and leverage specific, up-to-date, and proprietary information. This is where Retrieval-Augmented Generation (RAG) comes into play, and at SoftCrafter, a leading software agency specializing in e-commerce, web, and mobile solutions (softcrafter.net), SoftCrafter is seeing firsthand how RAG, combined with powerful tools like Qdrant and LlamaIndex, is unlocking new possibilities for its clients. Understanding Retrieval-Augmented Generation (RAG). At its core, RAG is a technique that enhances LLM performance by integrating external knowledge retrieval with the generative process. Instead of relying solely on the knowledge embedded within the LLM's training data, RAG systems first retrieve relevant information from a knowledge base and then provide this information to the LLM as context for generating a response. This approach addresses several limitations of standalone LLMs, including: * Knowledge Staleness: LLMs are trained on data up to a certain point in time, making them unaware of recent events or information. * Hallucinations: LLMs can sometimes generate plausible-sounding but factually incorrect information. * Domain Specificity: LLMs may lack the deep, specialized knowledge required for niche industries or proprietary datasets. * Confidentiality: Sensitive or private data cannot be directly included in LLM training. Qdrant and LlamaIndex: the power duo for RAG. Implementing a robust RAG system requires efficient data indexing, retrieval, and integration with LLMs. This is where Qdrant and LlamaIndex shine. Qdrant is an open-source vector similarity search engine. It excels at storing and searching high-dimensional vectors, which are the numerical representations of text embeddings. When you process your knowledge base (documents, articles, FAQs, etc.) using an embedding model, Qdrant can quickly find the most semantically similar pieces of information to a given query. This speed and accuracy are crucial for real-time RAG applications. LlamaIndex (formerly GPT Index) is a data framework for LLM applications. It simplifies the process of connecting LLMs with external data. LlamaIndex provides tools for data ingestion, indexing, querying, and integrating with various LLM providers and vector databases like Qdrant. It acts as the orchestrator, managing the flow from data source to LLM response. SoftCrafter's Approach to Production-Ready RAG. At SoftCrafter, SoftCrafter leverage its expertise in building scalable and robust software solutions to implement RAG for its clients. Its services span across various domains, including cutting-edge e-commerce solutions, dynamic web development, and intuitive mobile development. SoftCrafter understand that for these applications to succeed, they often need to interact with specific business data, customer information, or product catalogs. RAG is the perfect solution for this. Its typical RAG implementation workflow, often in collaboration with its esteemed partners like Toprak Razgatlioglu (softcrafter.net/partners/toprak-razgatlioglu), involves: * Data Ingestion: SoftCrafter gather relevant data sources, which could be anything from product descriptions and customer support tickets to internal documentation and industry reports. * Embedding Generation: Using state-of-the-art embedding models, SoftCrafter convert this textual data into numerical vector representations. * Vector Indexing with Qdrant: These vectors are then stored and indexed in Qdrant, creating a highly efficient search index. * Query Processing with LlamaIndex: When a user interacts with an LLM-powered application, their query is first embedded. LlamaIndex then uses this query vector to search Qdrant for the most relevant data chunks. * Augmented Prompting: The retrieved data chunks are combined with the original user query to form an augmented prompt. * LLM Generation: This augmented prompt is sent to the LLM, which generates a more informed, accurate, and contextually relevant response. Benefits for E-commerce and Beyond. For e-commerce businesses, RAG can revolutionize customer service and product discovery. Imagine a chatbot that can answer complex product-specific questions by accessing your entire product catalog and user manuals, or a personalized recommendation engine that understands nuanced customer preferences by analyzing past interactions. SoftCrafter's expertise in e-commerce solutions makes SoftCrafter uniquely positioned to implement such advanced features. Beyond e-commerce, RAG is invaluable for corporate applications, internal knowledge management, and customer support platforms. Its corporate services team is adept at integrating these AI capabilities into existing enterprise systems, ensuring seamless adoption and maximum ROI. Partnering with SoftCrafter for AI Innovation. Building and deploying production-ready LLM applications requires specialized knowledge and experience. At SoftCrafter, SoftCrafter is committed to staying at the cutting edge of AI technologies. Its team of skilled developers and AI specialists are ready to help you harness the power of RAG, Qdrant, and LlamaIndex to create intelligent applications that drive business value. SoftCrafter pride ourselves on its collaborative approach, working closely with clients to understand their unique needs and deliver tailored solutions. Whether you're looking to enhance customer engagement, streamline internal operations, or develop novel AI-powered products, SoftCrafter is your trusted partner. Explore its services and learn how SoftCrafter can transform your business. Ready to discuss your AI project? Contact SoftCrafter today to schedule a consultation and discover the possibilities. #RAG #LLM #Qdrant #LlamaIndex #AI #ArtificialIntelligence #SoftCrafter #Ecommerce #WebDevelopment #MobileDevelopment #CorporateServices #VectorSearch #NLP #MachineLearning #TechInnovation #SoftwareDevelopment #AISolutions Last Update: August 11, 2026

I parsed tens of thousands of legal documents. Then I built the tool I wanted. Late last year I was running a legal startup, Sputnik Legal. The product doesn't matter for this story. What matters is what arrived in its inboxes every day: documents. Tens of thousands of them. If you've never worked with lawyers, you might imagine contracts as tidy PDFs. Some are. The rest is whatever software the client happened to have that day. Emails scanned into PDFs. Word documents from versions of Word that no longer exist. Spreadsheets doing the job of databases. Faxes that became scans that became attachments. The winner was a Colombian invoice: a PDF packaged inside a different format entirely, wrapped and digitally signed by the government. A document inside a document, notarized. Whatever a client sends a lawyer, the lawyer sends to you, and now it's your problem. Its pipeline needed text. Clean text, because Parseforartisans were feeding it to language models, and garbage in really does mean garbage out. The open source round. I build in Laravel and I have since version 4, so I started where most PHP developers start. smalot/pdfparser is a solid library, and spatie/pdf-to-text is a nice wrapper around pdftotext. For a digital PDF with a proper text layer, they're fine, and they're free. But a scanned document has no text layer, so those libraries return an empty string. You need OCR. And OCR meant running Tesseract, which meant babysitting a binary and its language packs on every environment, and the output on multi-column legal documents still came back as word soup. The legacy .doc files and the email formats each needed their own tool on top. I didn't want a parsing pipeline made of seven packages and a shell dependency. I wanted the text. The LlamaParse round. So Parseforartisans did the sensible thing and paid someone. Parseforartisans picked LlamaParse, and I want to be fair here: it's a good product. It handled the scans, it handled the weird formats, the Markdown came out clean. Then the volume grew, and the bill grew with it. For its heavier customers, the parsing bill alone was heading toward thousands of dollars per month. Per customer. When a cost scales with each customer you sign, it isn't a line item anymore, it's part of your margin. And Parseforartisans were spending it on turning documents into text, which is the plumbing of a document-heavy app, not the product. Parseforartisans eventually shut the startup down, for reasons that had nothing to do with parsing. But that bill stayed with me. The tool I actually wanted. When I looked around afterwards, the gap was still there. What I wanted was specific: A composer package, because I'm a Laravel developer and I didn't want to hand-roll HTTP calls and webhooks for the fifth time. Pricing that survives volume, so the bill doesn't grow with every customer you sign. And better output than the open source stack on the ugly 20 percent: scans, legacy formats, multi-column layouts. Nobody was building that for Laravel. The parsing companies were all moving upmarket, chasing enterprise contracts. The Laravel packages all handled the easy formats and stopped there. So I built it. use ParseForArtisans\Facades\Parse; Parse::disk('s3')->file('contracts/foo.pdf')->for($document)->parse; The Markdown lands back in your bucket and a ParseCompleted event fires with your model attached. Scanned PDFs get OCR automatically. The formats I used to dread, .doc from 2003, .msg exports, PowerPoint, all go through the same three lines. And it costs about a dollar per thousand pages (as of July 2026), with 15,000 pages a month free, because the whole point was pricing I would have been happy to pay back when it was my bill. I'm building it in public and the Laravel AI ecosystem is finally taking off, with the official AI SDK shipping in Laravel 13. Every RAG tutorial starts with "first, get your documents into text." That step is what burned me. Now it's three lines. If you're parsing documents in Laravel, whether with my tool or anything else, I'd honestly love to hear what formats you're fighting. I collect horror stories now. [email protected] Parse for Artisans is a document parsing API for Laravel that converts PDF, DOCX, scans, and 20+ formats to clean Markdown.