ModelsDocsBlogEnterpriseLM LinkNew

Login or Signup

Models

Developer Docs

LM Link

Careers

Blog

Changelog

Enterprise Solutions

Privacy Policy

Terms of Use

👾 Element Labs, Inc. © 2026

LinkedIn GitHub Discord Twitter / X

Product

Download the app Models LM LinkNew LM Studio Hub Beta Releases Changelog

Developer

Developer Docs lmstudio-js lmstudio-python LM Studio CLI (lms)llms.txt llms-full.txt

Company

CareersWe're Hiring!

Enterprise Solutions

Legal

ceveyne/user-docs • LM Studio Hub

user-docs

Public

user-docs
/
docs
/
CHANGELOG.md

Project Files

dist

fpzip

src

fpzip

decompress.js

fpzip_loader.js

decompress

decompress.js

fpzip_loader.js

fpzip_wasm.js

fpzip_wasm.wasm

package.json

helpers

package.json

python

docling_parser.py

extract_image_page.py

pymupdf_parser.py

requirements.txt

cli.js

fpzip_wasm.js

fpzip_wasm.wasm

index.js

docs

initial-docs

ANNOTATE-IMAGE-DETECTION.md

MEMORIZE-DOC-IMAGES.md

SETUP.md

USER-DOCS.md

CHANGELOG.md

DEPLOYMENT.md

USER_GUIDE.md

python

docling_parser.py

extract_image_page.py

pymupdf_parser.py

requirements.txt

src

documents

parsers

pdfParser.ts

textParser.ts

fileWatcher.ts

loader.ts

fpzip

decompress.ts

fpzip_bridge.cpp

fpzip_loader.ts

fpzip_wasm.js

fpzip_wasm.wasm

package.json

helpers

documentImages.ts

drawBboxesOnImage.ts

embedLocalImages.ts

frontmatter.ts

globalConfigReader.ts

pngMetadata.ts

readPngMetadata.ts

sequenceExtractor.ts

toolProgress.ts

videoAssembler.ts

visionCapabilityPrimer.ts

visionPromotionLog.ts

rag

bm25.ts

chunker.ts

embeddings.ts

retriever.ts

retrieverSingleton.ts

vectorStore.ts

services

chatExporter.ts

lmStudioVisionAnalyzer.ts

toolResultHarvester.ts

userDocsGuidePrimer.ts

sources

adapters

githubMarkdownSourceAdapter.ts

huggingFaceMarkdownSourceAdapter.ts

lmStudioConversationSourceAdapter.ts

staticHtmlSourceAdapter.ts

http.ts

lmStudioConversationMarkdown.ts

normalizer.ts

registry.ts

remoteImageResolver.ts

types.ts

tools

analyse_image.ts

annotate_image.ts

detect_object.ts

export_doc.ts

extract_image.ts

fetch_image.ts

find_doc.ts

forget_doc.ts

memorize_doc.ts

read_config.ts

read_doc.ts

rewrite_doc.ts

show_image.ts

skip_doc.ts

types

external-shims.d.ts

utils

language.ts

pythonRunner.ts

ragLogger.ts

ragVenvSetup.ts

config.ts

core-bundle.mjs

index.ts

orchestrator.ts

promptPreprocessor.ts

thinkingToolCallParser.ts

toolsProvider.ts

types.ts

.gitignore

.lmsignore

.npmignore

.swcrc

build.mjs

LICENSE

manifest.json

mcp-shims.d.ts

package-lock.json

package.json

README.md

rollup.config.mjs

tsconfig.json

docs / CHANGELOG.md

Changelog

Notable changes to this project will be documented in this file.

Distribution

Source Code: LM Studio Hub
Documentation: GitHub Repository

[0.1.6] - 2026-06-20 Revision 6

Changed

annotate_image tool-result JSON no longer echoes the caller-supplied detection task; detection state and audit metadata still keep the internal task where needed.

[0.1.5] - 2026-06-20 Revision 5

Changed

Vision inference for analyse_image and annotate_image now uses only the configured embeddingBaseUrl / LM-Studio-compatible Vision API path; the legacy local Python/FastVLM backend was removed.
Cleaned up settings by removing legacy local vision server endpoint, TTL, and port options while keeping API token, model, prompt, max-token, and temperature controls.

[0.1.4] - 2026-06-17 Revision 4

Changed

Vision primer now uses a two-phase lazy-init flow (core 4B at startup, policy-resolved model on first generate) to avoid duplicate model loading and ensure correct config resolution.
Updated user documentation (README.md)

[0.1.3] - 2026-06-14 Revision 3

Changed

Enhanced tool descriptions.
Fine-tuned tool results.

[0.1.2] - 2026-06-13 Revision 2

Changed

Updated user documentation (README.md, USER_GUIDE.md, DEPLOYMENT.md).

[0.1.1] - 2026-06-12 Revision 1

Added

Initial release
User-centered knowledge-support
PDF as document-type (including complex, table and image-loaded PDF files)
indexing various content directories
indexing LM Studio conversations
image-based answers including annotated screenshots
host, develop and use complex agentic workflows
enable your vision-capable agent to review images from your personal knowledge base
generate ready-to-use image-based documents