visionbridge

KO | EN

gitlite — search

#typescript #ai-agents #ai #dsh-plugin #deepseek-harness #open-source #claude-code #codex #cli #developer-tools #react #windows

★ 47 Open GitHub ↗

Give text-only LLMs vision. A tiny OpenAI-compatible proxy that lets reasoning models (DeepSeek, Qwen, GLM…) see images by querying a separate vision model through tools: look, OCR, scan, crop, compare. No training, no weights.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# VisionBridge

Give text-only LLMs vision through a tiny OpenAI-compatible proxy.

VisionBridge sits between your chat UI and your models. It lets a reasoning model
from LM Studio, Ollama, vLLM, Z.ai, OpenRouter, or any OpenAI-compatible backend
inspect images by asking a separate vision model targeted questions.

No training. No weights. Bring your own reasoning model and your own vision model.

## How It Works

```text
OpenWebUI / LibreChat / app
        |
        v
VisionBridge at /v1/chat/completions
        |
        +-- reasoning model: LM Studio / Ollama / vLLM / GLM / DeepSeek
        |
        +-- vision model: LLaVA / Qwen-VL / GLM-V / GPT-4o-mini / any VLM
```

VisionBridge receives an OpenAI-style chat request. If the request contains
images, it stores the images, rewrites the prompt for the reasoning model, and
lets the reasoning model call tools:

- `look(image_id, question)` for targeted visual inspection
- `ocr(image_id)` for text extraction
- `scan(image_id)` for a tiled full-document text sweep of dense pages
- `crop_and_look(image_id, box, question)` for zooming into a region
  (small crops are automatically upscaled before the VLM sees them)
- `compare(image_id_a, image_id_b, question)` for judging two images together

The vision model does the seeing. The reasoning model does the thinking.

Before the loop starts, every image gets a one-shot **scene description** from
the vision model (in parallel, cached by content), so the reasoning model
begins with global context and spends its tool budget on details. Multiple
tool calls in one turn run **concurrently**, and repeated images across a
conversation are served from a content-addressed cache instead of being
re-fetched and re-decoded.

Tool calling uses the backend's **native OpenAI function calling** when
available. In the default `TOOL_MODE=auto`, VisionBridge probes the reasoning
backend once and transparently falls back to a prompt-JSON protocol for
backends and models that don't support tools — so it works with strong hosted
models and weak local ones alike.

The loop is built to survive imperfect models: hallucinated image ids, bad
crop boxes, malformed JSON, and vision-backend hiccups are fed back to the
reasoning model as observations so it can correct itself, and hitting the
inspection limit triggers a final best-effort answer instead of an error.

## Quick Start With Docker

```bash
docker run -p 8080:8080 \
  -e REASONING_BASE_URL=http://host.docker.internal:1234/v1 \
  -e REASONING_API_KEY=lm-studio \
  -e REASONING_MODEL=local-model \
  -e VISION_BASE_URL=http://host.docker.internal:11434/v1 \
  -e VISION_API_KEY=ollama \
  -e VISION_MODEL=llava:13b \
  ghcr.io/eekosystems/visionbridge:latest
```

Then point your OpenAI-compatible client at:

```text
Base URL: http://localhost:8080/v1
API key: anything
Model: visionbridge
```

## Local Development

```bash
cd visionbridge
python -m venv .venv
source .venv/bin/activate    # Windows: .venv\Scripts\activate
pip install -e ".[dev]"
cp .env.example .env         # Windows: copy .env.example .env
visionbridge serve --host 0.0.0.0 --port 8080
```

Check your backend configuration any time with:

```bash
visionbridge doctor
```

It verifies both backends are reachable, that the configured models exist, and
that a test completion succeeds.

## Configuration

All settings come from environment variables (or `.env`):

| Variable | Default | Purpose |
| --- | --- | --- |
| `REASONING_BASE_URL` | `http://localhost:1234/v1` | Reasoning backend |
| `REASONING_API_KEY` | `local` | Reasoning API key |
| `REASONING_MODEL` | `local-model` | Reasoning model id |
| `VISION_BASE_URL` | `http://localhost:11434/v1` | Vision backend |
| `VISION_API_KEY` | `local` | Vision API key |
| `VISION_MODEL` | `llava:13b` | Vision model id |
| `BRIDGE_MODEL_NAME` | `visionbridge` | Model name the proxy advertises |
| `TOOL_MODE` | `auto` | `auto`, `native`, or `prompt` tool calling |
| `MAX_VISION_CALLS` | `8` | Reasoning turns before a forced final answer |
| `REQUEST_TIMEOUT_SECONDS` | `120` | Per-backend-call timeout |
| `BACKEND_MAX_RETRIES` | `2` | Retries on 429/5xx/transport errors |
| `SCENE_PRIMING` | `true` | Describe each image once before the loop starts |
| `ALLOW_FILE_URLS` | `false` | Allow `file://` image URLs |
| `ALLOW_PRIVATE_URLS` | `false` | Allow image fetches from private/internal hosts |
| `MAX_IMAGE_BYTES` | `20971520` | Max bytes per image |
| `MAX_IMAGES_PER_REQUEST` | `16` | Max images per request |
| `IMAGE_CACHE_ENTRIES` | `64` | Content-addressed image cache size |
| `ENABLE_TRACES` | `true` | Keep tool-loop traces for `/v1/traces/{id}` |
| `BRIDGE_API_KEYS` | *(empty)* | Comma-separated keys; when set, `/v1/*` requires one |
| `EXTRA_MODELS` | *(empty)* | JSON map of extra model names to backend pairs |
| `LOG_JSON` | `false` | Emit JSON log lines |

### Serving multiple model pairs

One instance can serve several reasoning+vision pairs under different model
names. Unspecified fields inherit from the default pair:

```env
EXTRA_MODELS={"visionbridge-fast": {"reasoning": {"model": "qwen3:8b"}, "vision": {"model": "llava:7b"}}}
```

(or point `EXTRA_MODELS_FILE` at a JSON file). All names appear in
`GET /v1/models`, and clients select a pair with the `model` field.

## LM Studio Backend

1. Open LM Studio.
2. Load your reasoning model.
3. Go to the Developer tab and start the local server.
4. Use the default base URL:

```env
REASONING_BASE_URL=http://localhost:1234/v1
REASONING_API_KEY=lm-studio
REASONING_MODEL=local-model
```

LM Studio can also be used as the vision backend if you load a vision-capable
model and expose it through the same OpenAI-compatible server.

## Ollama Backend

```env
REASONING_BASE_URL=http://localhost:11434/v1
REASONING_API_KEY=ollama
REASONING_MODEL=qwen3:32b

VISION_BASE_URL=http://localhost:11434/v1
VISION_API_KEY=ollama
VISION_MODEL=llava:13b
```

## vLLM Backend

```env
REASONING_BASE_URL=http://localhost:8000/v1
REASONING_API_KEY=token-abc123
REASONING_MODEL=Qwen/Qwen3-32B

VISION_BASE_URL=http://localhost:8001/v1
VISION_API_KEY=token-abc123
VISION_MODEL=Qwen/Qwen3-VL-8B-Instruct
```

## OpenWebUI Setup

In OpenWebUI:

```text
Admin Panel -> Settings -> Connections -> OpenAI-compatible
Base URL: http://host.docker.internal:8080/v1
API Key: anything
Model: visionbridge
```

## API Surface

VisionBridge intentionally exposes the small subset most clients need:

- `GET /health` (add `?probe=true` to verify both backends are reachable)
- `GET /v1/models`
- `POST /v1/chat/completions`
- `GET /v1/traces/{completion_id}` — the full tool-loop trace for a recent
  request: every tool call, its arguments, the vision model's observation, and
  timings. Invaluable for answering "why did it say that?"

Responses include a `usage` block aggregated across every reasoning and vision
call made for the request, and an `X-Request-ID` header for correlating logs.

**Streaming**: image-free requests are streamed token-by-token straight from
the reasoning backend. Requests with images stream too: SSE heartbeats keep
the connection alive while tools run, and in native tool-calling mode the
final answer is forwarded token-by-token as the reasoning model produces it
(prompt-JSON mode buffers the loop and streams the answer in chunks).

**Errors**: backend failures return HTTP 502, invalid inputs 400.

**Auth**: set `BRIDGE_API_KEYS=key1,key2` to require a Bearer key on `/v1/*`
endpoints (`/health` stays open). For anything internet-facing, still prefer a
reverse proxy with TLS in front.

## Security Notes

Image URL fetching is hardened by default: hosts resolving to private,
loopback, or link-local addresses are rejected (SSRF guard), redirects are
validated hop-by-hop, downloads are size-capped, and payloads must decode as
real images. Run VisionBridge behind your own reverse proxy / auth layer if
you expose it beyond localhost — it deliberately ships without built-in auth.

## Benchmarks

`benchmarks/` contains a harness that scores VisionBridge against a direct
VLM (relaxed accuracy + ANLS) on DocVQA-style JSONL task sets. See
[benchmarks/README.md](benchmarks/README.md).

## Status

Actively developed. See [CHANGELOG.md](CHANGELOG.md) for what's new in 0.2.0.
Next up:

- published benchmark numbers against caption-only prompting
- persistent on-disk image/primer cache
- OpenWebUI and LibreChat screenshots

Contributions welcome — see [CONTRIBUTING.md](CONTRIBUTING.md).

## License

MIT

visionbridge

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README