Ollama FIM

A minimal VS Code extension that provides inline (ghost-text) code completions using Fill-In-the-Middle (FIM) models via Ollama.

Features

Ghost-text completions as you type, powered by FIM-capable models
Multi-model support: Works with rnj-1, DeepSeek-Coder, Qwen3-Coder, Gemma3, and Codestral/Ministral
FIM-optimized: Uses each model's native FIM tokens for best results
Minimal configuration: just set your Ollama URL and choose your model family
Debounced, cancellable requests to avoid hammering your backend

Supported Models

Family	Format	Example Model ID
rnj-1	<\|pre_fim\|>...<\|suf_fim\|>...<\|mid_fim\|>	`rnj-1:8b-cloud`
deepseek	<\|fim_begin\|>...<\|fim_hole\|>...<\|fim_end\|>	`deepseek-coder-v2:lite-instruct`
qwen	<\|fim_prefix\|>...<\|fim_suffix\|>...<\|fim_middle\|>	`qwen3-coder-next:latest`
gemma	<\|fim_prefix\|>...<\|fim_middle\|>...<\|fim_suffix\|>	`gemma3:latest`
mistral	<\|fim_prefix\|>...<\|fim_suffix\|>...<\|fim_middle\|>	`codestral:latest`

Requirements

VS Code 1.90+
Ollama running with your chosen FIM model pulled

Setup

Install Ollama: https://ollama.com
Pull your chosen model (e.g., rnj-1):
```
ollama pull rnj-1:8b-cloud
```
Start Ollama (usually runs on http://localhost:11434)
Configure the extension settings to match your model

Extension Settings

Setting	Type	Default	Description
`fim.enabled`	`boolean`	`true`	Enable/disable inline completions
`fim.apiUrl`	`string`	`http://localhost:11434`	Base URL of the Ollama API endpoint
`fim.maxTokens`	`number`	`256`	Maximum tokens to generate per completion
`fim.model`	`enum`	`rnj-1`	Model family (rnj-1, deepseek, qwen, gemma, mistral)
`fim.modelId`	`string`	(from family)	Specific Ollama model ID to use

Build

npm install
npm run compile

Test

npm test

Run

Open this folder in VS Code and press F5 to launch the Extension Development Host. Open any file, start typing, and ghost-text completions should appear if your backend is running and fim.model is set.

Release Notes

0.3.0

Renamed extension to "Ollama FIM" for clarity
Added GPL-3.0 license
Added file context options for better completions:
- fim.includeFileContext - Include imports, class definitions, function signatures
- fim.includeScopeInfo - Include current scope information (e.g., "in class MyClass > function myMethod")
- fim.fileContextChars - Configure max characters for file context
Fixed README table rendering for GitHub
Improved logging to show only model name instead of full request

0.2.0

Added support for multiple FIM model families:
- DeepSeek-Coder-V2 (deepseek)
- Qwen3-Coder (qwen)
- Gemma3 (gemma)
- Codestral/Ministral (mistral)
Added fim.model setting to select model family with token format descriptions
Added fim.modelId setting for custom model IDs
Updated default maxTokens to 256
Cleaned up dead code and removed invalid tests

0.1.0

Initial release with basic FIM inline completions for rnj-1 model.

Ollama FIM

guzmandrade-dev

Ollama FIM

Features

Supported Models

Requirements

Setup

Extension Settings

Build

Test

Run

Release Notes

0.3.0

0.2.0

0.1.0