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

Chalk Labs

Need help deploying multimodal_rag?

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.

Book a call

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.

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

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.

Signals

Stars: 5
Forks: 1
Open issues: 0
Last commit (this folder): Oct 18, 2026 (13 days ago)
Last release: Oct 18, 2026 (13 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: GitHub github-graphql

More from lasertsole

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 multimodal_rag 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.

Need help deploying multimodal_rag?

Call Get help

Cite this page

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

multimodal_rag

Need help deploying multimodal_rag?

Install

About

Reviews

Permissions

Network hosts it talks to 18

Files it touches

What's inside

More from lasertsole/sherry_agent

Signals

Details

More from lasertsole

Rather not set it up yourself?

Get multimodal_rag running in your business