Skip to content
Agentmart
Submit a tool

multimodal_rag

Private knowledge base for indexing multimodal files or folders into a knowledge graph, supporting multi-hop graph retrieval

Skill by lasertsole

IndexedMIT★ 5
Write a review

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/lasertsole-multimodal-rag

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.

We use your email only for this newsletter. Privacy

About

Private knowledge base for indexing multimodal files or folders into a knowledge graph, supporting multi-hop graph retrieval

Use cases: ml

Reviews

Write a review

No 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 and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 18

  • api.cohere.com · found in code
  • api.jina.ai · found in code
  • api.openai.com · found in code
  • api.siliconflow.cn · found in code
  • codeload.github.com · found in install command
  • dashscope.aliyuncs.com · found in code
  • generativelanguage.googleapis.com · found in code
  • github.com · found in code
  • integrate.api.nvidia.com · found in code
  • libreoffice.org · found in code
  • mineru.net · found in code
  • my-server.com · found in code
  • ollama.com · found in code
  • paddlepaddle.org.cn · found in code
  • pandoc.org · found in code
  • schemas.microsoft.com · found in code
  • schemas.openxmlformats.org · found in code
  • your-resource.openai.azure.com · found in code

Files it touches

  • ~/.claude/skills/multimodal-rag
  • /etc/x
  • /usr/share/fonts/wqy-microhei/wqy-microhei.ttc
  • Your home directory (~)

What's inside

Skill name
multimodal_rag
Description
Private knowledge base for indexing multimodal files or folders into a knowledge graph, supporting multi-hop graph retrieval
License
MIT
Instructions
36 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed

Files (149)

  • README.ja.md
  • README.ko.md
  • README.md
  • README.zh.md
  • SKILL.md
  • __init__.py
  • __init__.py · scripts/
  • __init__.py · scripts/graph_rag/
  • __init__.pyi · scripts/graph_rag/
  • base.py · scripts/graph_rag/
  • core.py · scripts/graph_rag/
  • ensure_mineru_models.py · scripts/graph_rag/
  • loop_patch.py · scripts/graph_rag/
  • __init__.py · scripts/graph_rag/vendored_lightrag/
  • _version.py · scripts/graph_rag/vendored_lightrag/
  • addon_params.py · scripts/graph_rag/vendored_lightrag/
  • base.py · scripts/graph_rag/vendored_lightrag/
  • chunk_schema.py · scripts/graph_rag/vendored_lightrag/
  • __init__.py · scripts/graph_rag/vendored_lightrag/chunker/
  • paragraph_semantic.py · scripts/graph_rag/vendored_lightrag/chunker/
  • recursive_character.py · scripts/graph_rag/vendored_lightrag/chunker/
  • semantic_chunker.py · scripts/graph_rag/vendored_lightrag/chunker/
  • semantic_vector.py · scripts/graph_rag/vendored_lightrag/chunker/
  • token_size.py · scripts/graph_rag/vendored_lightrag/chunker/
  • constants.py · scripts/graph_rag/vendored_lightrag/
  • __init__.py · scripts/graph_rag/vendored_lightrag/evaluation/
  • eval_rag_quality.py · scripts/graph_rag/vendored_lightrag/evaluation/
  • offline_retrieval_check.py · scripts/graph_rag/vendored_lightrag/evaluation/
  • exceptions.py · scripts/graph_rag/vendored_lightrag/
  • file_atomic.py · scripts/graph_rag/vendored_lightrag/
  • __init__.py · scripts/graph_rag/vendored_lightrag/kg/
  • factory.py · scripts/graph_rag/vendored_lightrag/kg/
  • shared_storage.py · scripts/graph_rag/vendored_lightrag/kg/
  • snkv_doc_status_impl.py · scripts/graph_rag/vendored_lightrag/kg/
  • snkv_graph_impl.py · scripts/graph_rag/vendored_lightrag/kg/
  • snkv_kv_impl.py · scripts/graph_rag/vendored_lightrag/kg/
  • snkv_shared.py · scripts/graph_rag/vendored_lightrag/kg/
  • snkv_vector_impl.py · scripts/graph_rag/vendored_lightrag/kg/
  • lightrag.py · scripts/graph_rag/vendored_lightrag/
  • __init__.py · scripts/graph_rag/vendored_lightrag/llm/
  • _vision_utils.py · scripts/graph_rag/vendored_lightrag/llm/
  • anthropic.py · scripts/graph_rag/vendored_lightrag/llm/
  • azure_openai.py · scripts/graph_rag/vendored_lightrag/llm/
  • bedrock.py · scripts/graph_rag/vendored_lightrag/llm/
  • binding_options.py · scripts/graph_rag/vendored_lightrag/llm/
  • siliconcloud.py · scripts/graph_rag/vendored_lightrag/llm/deprecated/
  • gemini.py · scripts/graph_rag/vendored_lightrag/llm/
  • hf.py · scripts/graph_rag/vendored_lightrag/llm/
  • jina.py · scripts/graph_rag/vendored_lightrag/llm/
  • llama_index_impl.py · scripts/graph_rag/vendored_lightrag/llm/
  • lmdeploy.py · scripts/graph_rag/vendored_lightrag/llm/
  • lollms.py · scripts/graph_rag/vendored_lightrag/llm/
  • nvidia_openai.py · scripts/graph_rag/vendored_lightrag/llm/
  • ollama.py · scripts/graph_rag/vendored_lightrag/llm/
  • openai.py · scripts/graph_rag/vendored_lightrag/llm/
  • voyageai.py · scripts/graph_rag/vendored_lightrag/llm/
  • zhipu.py · scripts/graph_rag/vendored_lightrag/llm/
  • llm_roles.py · scripts/graph_rag/vendored_lightrag/
  • multimodal_context.py · scripts/graph_rag/vendored_lightrag/
  • namespace.py · scripts/graph_rag/vendored_lightrag/
  • …and 89 more

SKILL.md (first lines)

**Index all files under a directory into the rag-anything graph:**

```python
import asyncio
from skills.builtin.core.multimodal_rag.scripts import folder_index, file_index

if __name__ == "__main__":
    _classify_folder: str = "{placeholder}"  # <- replace with the knowledge graph category

    # Use this when the input is an entire folder
    _input_folder_path: str = (
        "{placeholder}"  # <- replace with the absolute path of the input folder
    )
    coro = folder_index(_input_folder_path, _classify_folder)

    # Use this when the input is a single file
    # _input_file_path: str = "{placeholder}"  # <- replace with the absolute path of the input file
    # coro = file_index(_input_file_path, _classify_folder)

    # Run
    res = asyncio.run(coro)
    print(res)
```

**Query the rag-anything knowledge graph:**

```python
import asyncio
from skills.builtin.core.multimodal_rag.scripts import query

if __name__ == "__main__":
    _query: str = "{placeholder}"  # <- replace with the question
    res = asyncio.run(query(_query))
    print(res)
```

From lasertsole/sherry_agent, MIT.

More from lasertsole/sherry_agent

Signals

Stars
5
Forks
1
Open issues
0
Last commit (this folder)
Oct 18, 2026 (10 days ago)
Last release
Oct 18, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/lasertsole/sherry_agent
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from lasertsole

Cite this page

multimodal_rag skill. Agent Mart. https://agentmart.dev/skills/lasertsole-multimodal-rag (last updated 2026-10-24)