Lollms Multimodal Document and Image Parsing
Teaches how to import, parse, and process PDF, DOCX, PPTX, and image files using anchor-mapped and OCR import modes in LollmsDiscussion.
Skill by ParisNeo
Chalk Labs
Need help deploying Lollms Multimodal Document and Image Parsing?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/parisneo-lollms-multimodal-document-and-image-parsing
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, presentations
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/lollms-multimodal-document-and-image-parsing
What's inside
- Skill name
Lollms Multimodal Document and Image Parsing- Description
- Teaches how to import, parse, and process PDF, DOCX, PPTX, and image files using anchor-mapped and OCR import modes in LollmsDiscussion.
- License
- Apache-2.0
- Instructions
- 48 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Lollms Multimodal Document and Image Parsing" does not match folder "multimodal_parsing"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Lollms Multimodal Document and Image Parsing
This skill teaches how to import rich documents (PDF, Word, Slides) and image files into the LoLLMS system using appropriate import modes and anchor configurations.
## 1. Import Modes Overview
The file import subsystem supports four distinct operational modalities:
- `"text"`: Extracts plain text and Markdown only. No images are rendered.
- `"text_images"`: Extracts the text content and simultaneously renders pages/embedded images.
- `"images_only"`: Bypasses text extraction and converts the document strictly to high-resolution JPEG pages (great for scanned documents).
- `"ocr"`: Renders pages and passes them to a local/remote vision-capable LLM to transcribe the visual text, stitching results into a unified document.
## 2. Importing a Document with Anchors
To import a file, use the `import_file` method. For `text_images` mode, a companion image artifact (`<title>::images`) is created automatically. The text is populated with inline anchor tags:
```python
# Import a PDF report
result = discussion.import_file(
path="quarterly_report.pdf",
mode="text_images",
title="q2_report",
activate=True
)
print(f"Text artifact title: {result['text_artefact']['title']}")
print(f"Images artifact title: {result['image_artefact']['title']}")
print(f"Total pages rendered: {result['page_count']}")
```
The parsed text is injected into the prompt, containing inline reference anchors like:
`<artefact_image id="q2_report::images::0" />`
## 3. How the LLM Processes Anchors
- **Vision Map**: When the chat turn executes, the active companion images are appended to the model's vision input array.
- **Correlation**: The model reads the text anchors and correlates them with the image indexes in the vision input (e.g. image index #1 corresponds to the anchor `q2_report::images::0`).
- **Answering**: The model can then output the anchor verbatim in its response to reference specific figures, e.g.:
`"As we can observe in Figure 1, represented by <artefact_image id=\"q2_report::images::0\" />, the revenue increased..."`
## 4. Reconstructing and Bundling
All imported multimodal artifacts can be exported as a unified, self-contained JSON-serializable bundle containing both the text content and base64-encoded image files.
```python
# Export a bundle
bundle = discussion.artefacts.export_artefact_bundle("q2_report")
# Import the bundle back into an entirely different discussion session (restoring all sub-images)
restored_main = separate_discussion.artefacts.import_artefact_bundle(bundle, activate=True)
```From ParisNeo/lollms_client, Apache-2.0.
Signals
- Stars
- 13
- Forks
- 5
- Open issues
- 0
- Last commit (this folder)
- May 26, 2026 (5 months ago)
- Last release
- Mar 5, 2025 (1 year ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/ParisNeo/lollms_client
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Lollms Multimodal Document and Image Parsing running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Lollms Multimodal Document and Image Parsing skill. Agent Mart. https://agentmart.dev/skills/parisneo-lollms-multimodal-document-and-image-parsing (last updated 2026-10-24)