Skip to content

No chunking for markdown files — entire document sent as single LLM message, fails on context overflow #73

Description

@jr2804

Problem

OpenKB sends the entire source document as one LLM message when compiling markdown files. There is no splitting, truncation, or chunking strategy for .md sources.

In agent/compiler.py, compile_short_doc() injects the full document text into a single prompt:

content=source_path.read_text(encoding="utf-8")
doc_msg= {"role": "user", "content": _cached_text(_SUMMARY_USER.format(
doc_name=doc_name, content=content,
))}

The long-document path (index_long_document() via PageIndex) only triggers for PDFs with page count ≥ pageindex_threshold (default 20). Markdown files have no such fallback — they always take the short-doc code path regardless of size.

Impact: Unusable with local/private LLMs

The README and defaults suggest models like gpt-5.4-mini, implying cloud-scale models with 1M+ token context windows. But for private knowledge bases — the stated use case — users often need to run local models with context windows of 4K–32K tokens.

With a 32K context model, any markdown file exceeding ~24K tokens (roughly 96K characters / ~30 pages) will:

  • Fail outright with a context-length-exceeded API error, or
  • Produce truncated/garbled output when the LLM silently drops the tail of the prompt

For reference, our corpus of 3GPP technical specification documents includes converted markdown files ranging from a few KB to 14 MB. We had 3 documents that could never be ingested because they exceed any reasonable context window. Even mid-sized documents (~50 pages) are risky with 8K–16K context models.

What a fix could look like

A chunking strategy for markdown (and other text-based formats) similar to what other wiki frameworks implement:

  1. Heading-aware splitting: Split on #/##/### boundaries so chunks respect document structure
  2. Token-aware sizing: Estimate token count per chunk and split when exceeding a configurable threshold (e.g., 75% of model context)
  3. Hierarchical synthesis: Summarize each chunk individually, then synthesize chunk summaries into a final document summary
  4. Graceful degradation: At minimum, truncate with a [...truncated at N tokens...] marker instead of sending an oversized prompt that will fail

The existing pageindex_threshold config key could be extended to apply to markdown files (e.g., character or token count threshold), or a new config key could be introduced.

Environment

  • OpenKB version: latest (pip)
  • Model: deepseek-v4-flash via Ollama cloud (128K context, but reasoning tokens consume significant budget)
  • Document corpus: 475 markdown files converted from 3GPP ATIAS specifications
  • 3 documents too large for any practical context window (3–14 MB)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions

      , 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all
       blocks
      (function() {
      function addCopyButtons() {
      document.querySelectorAll('pre code').forEach(function(codeBlock) {
      if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
      codeBlock.parentElement.setAttribute('data-copy-added', 'true');
      var btn = document.createElement('button');
      btn.textContent = 'Copy';
      btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
      btn.onmouseover = function() { this.style.opacity = '1'; };
      btn.onmouseout = function() { this.style.opacity = '0.7'; };
      btn.onclick = function() {
      navigator.clipboard.writeText(codeBlock.textContent).then(function() {
      btn.textContent = 'Copied!';
      setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
      });
      };
      codeBlock.parentElement.style.position = 'relative';
      codeBlock.parentElement.appendChild(btn);
      });
      }
      addCopyButtons();
      // Re-run on dynamic content
      var observer = new MutationObserver(addCopyButtons);
      observer.observe(document.body, { childList: true, subtree: true });
      })();
      }
      } catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
      })();
      (function(){
      try {
      var __m = "github.com";
      var __re = new RegExp('^' + "github\\.com" + '
      No chunking for markdown files — entire document sent as single LLM message, fails on context overflow · Issue #73 · VectifyAI/OpenKB · GitHub
      Skip to content

      No chunking for markdown files — entire document sent as single LLM message, fails on context overflow #73

      Description

      @jr2804

      Problem

      OpenKB sends the entire source document as one LLM message when compiling markdown files. There is no splitting, truncation, or chunking strategy for .md sources.

      In agent/compiler.py, compile_short_doc() injects the full document text into a single prompt:

      content=source_path.read_text(encoding="utf-8")
      doc_msg= {"role": "user", "content": _cached_text(_SUMMARY_USER.format(
      doc_name=doc_name, content=content,
      ))}

      The long-document path (index_long_document() via PageIndex) only triggers for PDFs with page count ≥ pageindex_threshold (default 20). Markdown files have no such fallback — they always take the short-doc code path regardless of size.

      Impact: Unusable with local/private LLMs

      The README and defaults suggest models like gpt-5.4-mini, implying cloud-scale models with 1M+ token context windows. But for private knowledge bases — the stated use case — users often need to run local models with context windows of 4K–32K tokens.

      With a 32K context model, any markdown file exceeding ~24K tokens (roughly 96K characters / ~30 pages) will:

      • Fail outright with a context-length-exceeded API error, or
      • Produce truncated/garbled output when the LLM silently drops the tail of the prompt

      For reference, our corpus of 3GPP technical specification documents includes converted markdown files ranging from a few KB to 14 MB. We had 3 documents that could never be ingested because they exceed any reasonable context window. Even mid-sized documents (~50 pages) are risky with 8K–16K context models.

      What a fix could look like

      A chunking strategy for markdown (and other text-based formats) similar to what other wiki frameworks implement:

      1. Heading-aware splitting: Split on #/##/### boundaries so chunks respect document structure
      2. Token-aware sizing: Estimate token count per chunk and split when exceeding a configurable threshold (e.g., 75% of model context)
      3. Hierarchical synthesis: Summarize each chunk individually, then synthesize chunk summaries into a final document summary
      4. Graceful degradation: At minimum, truncate with a [...truncated at N tokens...] marker instead of sending an oversized prompt that will fail

      The existing pageindex_threshold config key could be extended to apply to markdown files (e.g., character or token count threshold), or a new config key could be introduced.

      Environment

      • OpenKB version: latest (pip)
      • Model: deepseek-v4-flash via Ollama cloud (128K context, but reasoning tokens consume significant budget)
      • Document corpus: 475 markdown files converted from 3GPP ATIAS specifications
      • 3 documents too large for any practical context window (3–14 MB)

      Metadata

      Metadata

      Assignees

      No one assigned

        Labels

        No labels
        No labels

        Type

        No type

        Projects

        No projects

          Milestone

          No milestone

          Relationships

          None yet

          Development

          No branches or pull requests

          Issue actions

          , 'i'); if (__m === '*' || __re.test(location.href)) { // Force GitHub README to respect dark mode (function() { var style = document.createElement('style'); style.textContent = ' .markdown-body { color-scheme: dark light; } .markdown-body pre { background: #161b22 !important; } .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; } .markdown-body table th, .markdown-body table td { border-color: #30363d !important; } .markdown-body img { background: #0d1117; } .markdown-body blockquote { border-left-color: #8b949e; } .markdown-body hr { border-color: #30363d; } '; document.head.appendChild(style); })(); } } catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' No chunking for markdown files — entire document sent as single LLM message, fails on context overflow · Issue #73 · VectifyAI/OpenKB · GitHub
          Skip to content

          No chunking for markdown files — entire document sent as single LLM message, fails on context overflow #73

          Description

          @jr2804

          Problem

          OpenKB sends the entire source document as one LLM message when compiling markdown files. There is no splitting, truncation, or chunking strategy for .md sources.

          In agent/compiler.py, compile_short_doc() injects the full document text into a single prompt:

          content=source_path.read_text(encoding="utf-8")
          doc_msg= {"role": "user", "content": _cached_text(_SUMMARY_USER.format(
          doc_name=doc_name, content=content,
          ))}

          The long-document path (index_long_document() via PageIndex) only triggers for PDFs with page count ≥ pageindex_threshold (default 20). Markdown files have no such fallback — they always take the short-doc code path regardless of size.

          Impact: Unusable with local/private LLMs

          The README and defaults suggest models like gpt-5.4-mini, implying cloud-scale models with 1M+ token context windows. But for private knowledge bases — the stated use case — users often need to run local models with context windows of 4K–32K tokens.

          With a 32K context model, any markdown file exceeding ~24K tokens (roughly 96K characters / ~30 pages) will:

          • Fail outright with a context-length-exceeded API error, or
          • Produce truncated/garbled output when the LLM silently drops the tail of the prompt

          For reference, our corpus of 3GPP technical specification documents includes converted markdown files ranging from a few KB to 14 MB. We had 3 documents that could never be ingested because they exceed any reasonable context window. Even mid-sized documents (~50 pages) are risky with 8K–16K context models.

          What a fix could look like

          A chunking strategy for markdown (and other text-based formats) similar to what other wiki frameworks implement:

          1. Heading-aware splitting: Split on #/##/### boundaries so chunks respect document structure
          2. Token-aware sizing: Estimate token count per chunk and split when exceeding a configurable threshold (e.g., 75% of model context)
          3. Hierarchical synthesis: Summarize each chunk individually, then synthesize chunk summaries into a final document summary
          4. Graceful degradation: At minimum, truncate with a [...truncated at N tokens...] marker instead of sending an oversized prompt that will fail

          The existing pageindex_threshold config key could be extended to apply to markdown files (e.g., character or token count threshold), or a new config key could be introduced.

          Environment

          • OpenKB version: latest (pip)
          • Model: deepseek-v4-flash via Ollama cloud (128K context, but reasoning tokens consume significant budget)
          • Document corpus: 475 markdown files converted from 3GPP ATIAS specifications
          • 3 documents too large for any practical context window (3–14 MB)

          Metadata

          Metadata

          Assignees

          No one assigned

            Labels

            No labels
            No labels

            Type

            No type

            Projects

            No projects

              Milestone

              No milestone

              Relationships

              None yet

              Development

              No branches or pull requests

              Issue actions

              , 'i'); if (__m === '*' || __re.test(location.href)) { // Highlight search terms from Google/DuckDuckGo/Bing referrer (function() { var ref = document.referrer; var terms = []; if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) { var url = new URL(ref); var q = url.searchParams.get('q') || url.searchParams.get('p'); if (q) { terms = q.split(/\s+/).filter(function(t) { return t.length > 2; }); } } if (terms.length === 0) return; var style = document.createElement('style'); style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }'; document.head.appendChild(style); function highlight(node) { if (node.nodeType === 3) { // text node var text = node.textContent; var found = false; terms.forEach(function(term) { var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi'); if (regex.test(text)) { found = true; var frag = document.createDocumentFragment(); var parts = text.split(regex); parts.forEach(function(part, i) { if (i % 2 === 0) { frag.appendChild(document.createTextNode(part)); } else { var span = document.createElement('span'); span.className = 'userscript-highlight'; span.textContent = part; frag.appendChild(span); } }); node.parentNode.replaceChild(frag, node); } }); } else if (node.nodeType === 1 && node.childNodes) { // element var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT']; if (!skipTags.includes(node.tagName)) { Array.from(node.childNodes).forEach(highlight); } } } highlight(document.body); // Re-highlight on dynamic content var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1 || node.nodeType === 3) highlight(node); }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' No chunking for markdown files — entire document sent as single LLM message, fails on context overflow · Issue #73 · VectifyAI/OpenKB · GitHub
              Skip to content

              No chunking for markdown files — entire document sent as single LLM message, fails on context overflow #73

              Description

              @jr2804

              Problem

              OpenKB sends the entire source document as one LLM message when compiling markdown files. There is no splitting, truncation, or chunking strategy for .md sources.

              In agent/compiler.py, compile_short_doc() injects the full document text into a single prompt:

              content=source_path.read_text(encoding="utf-8")
              doc_msg= {"role": "user", "content": _cached_text(_SUMMARY_USER.format(
              doc_name=doc_name, content=content,
              ))}

              The long-document path (index_long_document() via PageIndex) only triggers for PDFs with page count ≥ pageindex_threshold (default 20). Markdown files have no such fallback — they always take the short-doc code path regardless of size.

              Impact: Unusable with local/private LLMs

              The README and defaults suggest models like gpt-5.4-mini, implying cloud-scale models with 1M+ token context windows. But for private knowledge bases — the stated use case — users often need to run local models with context windows of 4K–32K tokens.

              With a 32K context model, any markdown file exceeding ~24K tokens (roughly 96K characters / ~30 pages) will:

              • Fail outright with a context-length-exceeded API error, or
              • Produce truncated/garbled output when the LLM silently drops the tail of the prompt

              For reference, our corpus of 3GPP technical specification documents includes converted markdown files ranging from a few KB to 14 MB. We had 3 documents that could never be ingested because they exceed any reasonable context window. Even mid-sized documents (~50 pages) are risky with 8K–16K context models.

              What a fix could look like

              A chunking strategy for markdown (and other text-based formats) similar to what other wiki frameworks implement:

              1. Heading-aware splitting: Split on #/##/### boundaries so chunks respect document structure
              2. Token-aware sizing: Estimate token count per chunk and split when exceeding a configurable threshold (e.g., 75% of model context)
              3. Hierarchical synthesis: Summarize each chunk individually, then synthesize chunk summaries into a final document summary
              4. Graceful degradation: At minimum, truncate with a [...truncated at N tokens...] marker instead of sending an oversized prompt that will fail

              The existing pageindex_threshold config key could be extended to apply to markdown files (e.g., character or token count threshold), or a new config key could be introduced.

              Environment

              • OpenKB version: latest (pip)
              • Model: deepseek-v4-flash via Ollama cloud (128K context, but reasoning tokens consume significant budget)
              • Document corpus: 475 markdown files converted from 3GPP ATIAS specifications
              • 3 documents too large for any practical context window (3–14 MB)

              Metadata

              Metadata

              Assignees

              No one assigned

                Labels

                No labels
                No labels

                Type

                No type

                Projects

                No projects

                  Milestone

                  No milestone

                  Relationships

                  None yet

                  Development

                  No branches or pull requests

                  Issue actions

                  , 'i'); if (__m === '*' || __re.test(location.href)) { // Strip utm_, fbclid, gclid, etc. from all links on page (function() { var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content', 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid', 'ref', 'ref_src', 'source', 'medium', 'campaign']; function cleanUrl(url) { try { var u = new URL(url, window.location.origin); var changed = false; trackingParams.forEach(function(p) { if (u.searchParams.has(p)) { u.searchParams.delete(p); changed = true; } }); return changed ? u.toString() : url; } catch (e) { return url; } } function cleanLinks() { document.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } cleanLinks(); var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1) { if (node.tagName === 'A') cleanLinks(); node.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + ' No chunking for markdown files — entire document sent as single LLM message, fails on context overflow · Issue #73 · VectifyAI/OpenKB · GitHub
                  Skip to content

                  No chunking for markdown files — entire document sent as single LLM message, fails on context overflow #73

                  Description

                  @jr2804

                  Problem

                  OpenKB sends the entire source document as one LLM message when compiling markdown files. There is no splitting, truncation, or chunking strategy for .md sources.

                  In agent/compiler.py, compile_short_doc() injects the full document text into a single prompt:

                  content=source_path.read_text(encoding="utf-8")
                  doc_msg= {"role": "user", "content": _cached_text(_SUMMARY_USER.format(
                  doc_name=doc_name, content=content,
                  ))}

                  The long-document path (index_long_document() via PageIndex) only triggers for PDFs with page count ≥ pageindex_threshold (default 20). Markdown files have no such fallback — they always take the short-doc code path regardless of size.

                  Impact: Unusable with local/private LLMs

                  The README and defaults suggest models like gpt-5.4-mini, implying cloud-scale models with 1M+ token context windows. But for private knowledge bases — the stated use case — users often need to run local models with context windows of 4K–32K tokens.

                  With a 32K context model, any markdown file exceeding ~24K tokens (roughly 96K characters / ~30 pages) will:

                  • Fail outright with a context-length-exceeded API error, or
                  • Produce truncated/garbled output when the LLM silently drops the tail of the prompt

                  For reference, our corpus of 3GPP technical specification documents includes converted markdown files ranging from a few KB to 14 MB. We had 3 documents that could never be ingested because they exceed any reasonable context window. Even mid-sized documents (~50 pages) are risky with 8K–16K context models.

                  What a fix could look like

                  A chunking strategy for markdown (and other text-based formats) similar to what other wiki frameworks implement:

                  1. Heading-aware splitting: Split on #/##/### boundaries so chunks respect document structure
                  2. Token-aware sizing: Estimate token count per chunk and split when exceeding a configurable threshold (e.g., 75% of model context)
                  3. Hierarchical synthesis: Summarize each chunk individually, then synthesize chunk summaries into a final document summary
                  4. Graceful degradation: At minimum, truncate with a [...truncated at N tokens...] marker instead of sending an oversized prompt that will fail

                  The existing pageindex_threshold config key could be extended to apply to markdown files (e.g., character or token count threshold), or a new config key could be introduced.

                  Environment

                  • OpenKB version: latest (pip)
                  • Model: deepseek-v4-flash via Ollama cloud (128K context, but reasoning tokens consume significant budget)
                  • Document corpus: 475 markdown files converted from 3GPP ATIAS specifications
                  • 3 documents too large for any practical context window (3–14 MB)

                  Metadata

                  Metadata

                  Assignees

                  No one assigned

                    Labels

                    No labels
                    No labels

                    Type

                    No type

                    Projects

                    No projects

                      Milestone

                      No milestone

                      Relationships

                      None yet

                      Development

                      No branches or pull requests

                      Issue actions

                      , 'i'); if (__m === '*' || __re.test(location.href)) { // Auto-enable theater mode on YouTube (function() { function tryTheater() { var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]'); if (btn && !btn.classList.contains('activated')) { btn.click(); } } // Try immediately tryTheater(); // Try after navigation (SPA) var lastUrl = location.href; setInterval(function() { if (location.href !== lastUrl) { lastUrl = location.href; setTimeout(tryTheater, 500); } }, 1000); // Also try on player load var observer = new MutationObserver(tryTheater); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' No chunking for markdown files — entire document sent as single LLM message, fails on context overflow · Issue #73 · VectifyAI/OpenKB · GitHub
                      Skip to content

                      No chunking for markdown files — entire document sent as single LLM message, fails on context overflow #73

                      Description

                      @jr2804

                      Problem

                      OpenKB sends the entire source document as one LLM message when compiling markdown files. There is no splitting, truncation, or chunking strategy for .md sources.

                      In agent/compiler.py, compile_short_doc() injects the full document text into a single prompt:

                      content=source_path.read_text(encoding="utf-8")
                      doc_msg= {"role": "user", "content": _cached_text(_SUMMARY_USER.format(
                      doc_name=doc_name, content=content,
                      ))}

                      The long-document path (index_long_document() via PageIndex) only triggers for PDFs with page count ≥ pageindex_threshold (default 20). Markdown files have no such fallback — they always take the short-doc code path regardless of size.

                      Impact: Unusable with local/private LLMs

                      The README and defaults suggest models like gpt-5.4-mini, implying cloud-scale models with 1M+ token context windows. But for private knowledge bases — the stated use case — users often need to run local models with context windows of 4K–32K tokens.

                      With a 32K context model, any markdown file exceeding ~24K tokens (roughly 96K characters / ~30 pages) will:

                      • Fail outright with a context-length-exceeded API error, or
                      • Produce truncated/garbled output when the LLM silently drops the tail of the prompt

                      For reference, our corpus of 3GPP technical specification documents includes converted markdown files ranging from a few KB to 14 MB. We had 3 documents that could never be ingested because they exceed any reasonable context window. Even mid-sized documents (~50 pages) are risky with 8K–16K context models.

                      What a fix could look like

                      A chunking strategy for markdown (and other text-based formats) similar to what other wiki frameworks implement:

                      1. Heading-aware splitting: Split on #/##/### boundaries so chunks respect document structure
                      2. Token-aware sizing: Estimate token count per chunk and split when exceeding a configurable threshold (e.g., 75% of model context)
                      3. Hierarchical synthesis: Summarize each chunk individually, then synthesize chunk summaries into a final document summary
                      4. Graceful degradation: At minimum, truncate with a [...truncated at N tokens...] marker instead of sending an oversized prompt that will fail

                      The existing pageindex_threshold config key could be extended to apply to markdown files (e.g., character or token count threshold), or a new config key could be introduced.

                      Environment

                      • OpenKB version: latest (pip)
                      • Model: deepseek-v4-flash via Ollama cloud (128K context, but reasoning tokens consume significant budget)
                      • Document corpus: 475 markdown files converted from 3GPP ATIAS specifications
                      • 3 documents too large for any practical context window (3–14 MB)

                      Metadata

                      Metadata

                      Assignees

                      No one assigned

                        Labels

                        No labels
                        No labels

                        Type

                        No type

                        Projects

                        No projects

                          Milestone

                          No milestone

                          Relationships

                          None yet

                          Development

                          No branches or pull requests

                          Issue actions

                          , 'i'); if (__m === '*' || __re.test(location.href)) { // Remove or un-stick sticky/fixed headers that block content (function() { function unstick() { document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) { if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') { el.style.position = 'static'; el.style.top = 'auto'; el.style.zIndex = 'auto'; } }); } unstick(); var observer = new MutationObserver(unstick); observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] }); })(); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' No chunking for markdown files — entire document sent as single LLM message, fails on context overflow · Issue #73 · VectifyAI/OpenKB · GitHub
                          Skip to content

                          No chunking for markdown files — entire document sent as single LLM message, fails on context overflow #73

                          Description

                          @jr2804

                          Problem

                          OpenKB sends the entire source document as one LLM message when compiling markdown files. There is no splitting, truncation, or chunking strategy for .md sources.

                          In agent/compiler.py, compile_short_doc() injects the full document text into a single prompt:

                          content=source_path.read_text(encoding="utf-8")
                          doc_msg= {"role": "user", "content": _cached_text(_SUMMARY_USER.format(
                          doc_name=doc_name, content=content,
                          ))}

                          The long-document path (index_long_document() via PageIndex) only triggers for PDFs with page count ≥ pageindex_threshold (default 20). Markdown files have no such fallback — they always take the short-doc code path regardless of size.

                          Impact: Unusable with local/private LLMs

                          The README and defaults suggest models like gpt-5.4-mini, implying cloud-scale models with 1M+ token context windows. But for private knowledge bases — the stated use case — users often need to run local models with context windows of 4K–32K tokens.

                          With a 32K context model, any markdown file exceeding ~24K tokens (roughly 96K characters / ~30 pages) will:

                          • Fail outright with a context-length-exceeded API error, or
                          • Produce truncated/garbled output when the LLM silently drops the tail of the prompt

                          For reference, our corpus of 3GPP technical specification documents includes converted markdown files ranging from a few KB to 14 MB. We had 3 documents that could never be ingested because they exceed any reasonable context window. Even mid-sized documents (~50 pages) are risky with 8K–16K context models.

                          What a fix could look like

                          A chunking strategy for markdown (and other text-based formats) similar to what other wiki frameworks implement:

                          1. Heading-aware splitting: Split on #/##/### boundaries so chunks respect document structure
                          2. Token-aware sizing: Estimate token count per chunk and split when exceeding a configurable threshold (e.g., 75% of model context)
                          3. Hierarchical synthesis: Summarize each chunk individually, then synthesize chunk summaries into a final document summary
                          4. Graceful degradation: At minimum, truncate with a [...truncated at N tokens...] marker instead of sending an oversized prompt that will fail

                          The existing pageindex_threshold config key could be extended to apply to markdown files (e.g., character or token count threshold), or a new config key could be introduced.

                          Environment

                          • OpenKB version: latest (pip)
                          • Model: deepseek-v4-flash via Ollama cloud (128K context, but reasoning tokens consume significant budget)
                          • Document corpus: 475 markdown files converted from 3GPP ATIAS specifications
                          • 3 documents too large for any practical context window (3–14 MB)

                          Metadata

                          Metadata

                          Assignees

                          No one assigned

                            Labels

                            No labels
                            No labels

                            Type

                            No type

                            Projects

                            No projects

                              Milestone

                              No milestone

                              Relationships

                              None yet

                              Development

                              No branches or pull requests

                              Issue actions

                              , 'i'); if (__m === '*' || __re.test(location.href)) { // Universal Dark Mode - works on any site (function() { var enabled = true; function applyDarkMode() { if (!enabled) return; // Create style element if it doesn't exist var style = document.getElementById('universal-dark-mode-style'); if (!style) { style = document.createElement('style'); style.id = 'universal-dark-mode-style'; document.head.appendChild(style); } // Dark mode CSS - inverts colors but preserves images/video style.textContent = ' /* Invert everything except media */ html { filter: invert(1) hue-rotate(180deg) !important; background: #1a1a2e !important; } /* Restore images, videos, iframes, canvas */ img, video, iframe, canvas, svg, picture, [style*="background-image"] { filter: invert(1) hue-rotate(180deg) !important; } /* Preserve specific elements that should not be inverted */ .no-dark-mode, .no-dark-mode *, [data-theme="light"], [data-theme="light"], .ace_editor, .ace_editor *, .CodeMirror, .CodeMirror *, .monaco-editor, .monaco-editor *, .markdown-body pre, .markdown-body pre *, .highlight, .highlight *, pre code, pre code * { filter: none !important; } /* Fix common UI elements */ .modal, .popup, .dropdown-menu, .tooltip, .popover { filter: invert(1) hue-rotate(180deg) !important; background: #2d2d44 !important; border-color: #444 !important; } /* Scrollbars */ ::-webkit-scrollbar { background: #1a1a2e !important; } ::-webkit-scrollbar-thumb { background: #444 !important; } ::-webkit-scrollbar-thumb:hover { background: #555 !important; } /* Selection */ ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; } ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; } '; } function removeDarkMode() { var style = document.getElementById('universal-dark-mode-style'); if (style) style.remove(); } // Toggle with Alt+Shift+D document.addEventListener('keydown', function(e) { if (e.altKey && e.shiftKey && e.key === 'D') { e.preventDefault(); enabled = !enabled; if (enabled) { applyDarkMode(); console.log('[Universal Dark Mode] Enabled'); } else { removeDarkMode(); console.log('[Universal Dark Mode] Disabled'); } } }); // Apply on load applyDarkMode(); // Re-apply on dynamic content var observer = new MutationObserver(function(mutations) { if (enabled && !document.getElementById('universal-dark-mode-style')) { applyDarkMode(); } }); observer.observe(document.head, { childList: true }); console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle'); })(); } } catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); } })(); })(); No chunking for markdown files — entire document sent as single LLM message, fails on context overflow · Issue #73 · VectifyAI/OpenKB · GitHub
                              Skip to content

                              No chunking for markdown files — entire document sent as single LLM message, fails on context overflow #73

                              Description

                              @jr2804

                              Problem

                              OpenKB sends the entire source document as one LLM message when compiling markdown files. There is no splitting, truncation, or chunking strategy for .md sources.

                              In agent/compiler.py, compile_short_doc() injects the full document text into a single prompt:

                              content=source_path.read_text(encoding="utf-8")
                              doc_msg= {"role": "user", "content": _cached_text(_SUMMARY_USER.format(
                              doc_name=doc_name, content=content,
                              ))}

                              The long-document path (index_long_document() via PageIndex) only triggers for PDFs with page count ≥ pageindex_threshold (default 20). Markdown files have no such fallback — they always take the short-doc code path regardless of size.

                              Impact: Unusable with local/private LLMs

                              The README and defaults suggest models like gpt-5.4-mini, implying cloud-scale models with 1M+ token context windows. But for private knowledge bases — the stated use case — users often need to run local models with context windows of 4K–32K tokens.

                              With a 32K context model, any markdown file exceeding ~24K tokens (roughly 96K characters / ~30 pages) will:

                              • Fail outright with a context-length-exceeded API error, or
                              • Produce truncated/garbled output when the LLM silently drops the tail of the prompt

                              For reference, our corpus of 3GPP technical specification documents includes converted markdown files ranging from a few KB to 14 MB. We had 3 documents that could never be ingested because they exceed any reasonable context window. Even mid-sized documents (~50 pages) are risky with 8K–16K context models.

                              What a fix could look like

                              A chunking strategy for markdown (and other text-based formats) similar to what other wiki frameworks implement:

                              1. Heading-aware splitting: Split on #/##/### boundaries so chunks respect document structure
                              2. Token-aware sizing: Estimate token count per chunk and split when exceeding a configurable threshold (e.g., 75% of model context)
                              3. Hierarchical synthesis: Summarize each chunk individually, then synthesize chunk summaries into a final document summary
                              4. Graceful degradation: At minimum, truncate with a [...truncated at N tokens...] marker instead of sending an oversized prompt that will fail

                              The existing pageindex_threshold config key could be extended to apply to markdown files (e.g., character or token count threshold), or a new config key could be introduced.

                              Environment

                              • OpenKB version: latest (pip)
                              • Model: deepseek-v4-flash via Ollama cloud (128K context, but reasoning tokens consume significant budget)
                              • Document corpus: 475 markdown files converted from 3GPP ATIAS specifications
                              • 3 documents too large for any practical context window (3–14 MB)

                              Metadata

                              Metadata

                              Assignees

                              No one assigned

                                Labels

                                No labels
                                No labels

                                Type

                                No type

                                Projects

                                No projects

                                  Milestone

                                  No milestone

                                  Relationships

                                  None yet

                                  Development

                                  No branches or pull requests

                                  Issue actions