Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
65 changes: 65 additions & 0 deletions docs/awesome-ollama-functions.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,65 @@


# Awesome Ollama Functions

Ollama is a powerful library for interacting with language models. Here are some of its most impressive functions:

## Core Functions

### `generate()`
- Generates text responses from prompts
- Supports streaming for real-time output
- Handles image inputs for multimodal models

### `chat()`
- Facilitates conversational interactions
- Manages message history and context
- Supports image inputs in messages

### `embed()`
- Creates vector embeddings from text input
- Useful for semantic search and text analysis

## Model Management

### `create()`
- Builds custom models from Modelfiles
- Supports quantization for optimized performance

### `pull()`
- Downloads models from the Ollama registry
- Supports progress tracking with streaming

### `push()`
- Uploads models to the Ollama registry
- Enables sharing and distribution of custom models

### `list()`
- Retrieves information about available models
- Provides details like model size and modification date

### `copy()`
- Duplicates existing models for customization
- Facilitates model versioning and experimentation

### `delete()`
- Removes models from the local system
- Helps manage storage and model versions

## Advanced Features

### `show()`
- Displays detailed metadata about a model
- Includes license, parameters, and system prompts

### `embeddings()`
- Creates vector representations of text
- Useful for semantic similarity and clustering tasks

### `parseModelfile()`
- Processes Modelfiles for custom model creation
- Handles file paths and blob hashing

These functions showcase Ollama's versatility in model interaction, management, and customization, making it a powerful tool for AI development and deployment.


50 changes: 50 additions & 0 deletions docs/best-practices/documentation-style-guide.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,50 @@
# Documentation Style Guide

## Overview

This style guide provides standards for creating clear, consistent, and high-quality documentation. Following these guidelines will help ensure our docs are professional, readable, and useful for our audience.

## General Principles

- Use clear, concise language
- Be consistent in terminology, formatting, and style
- Structure content logically with headings and lists
- Include relevant code samples and examples
- Link to related docs and resources

## Writing Style

- Use active voice and present tense
- Write in second person ("you") when addressing the reader
- Avoid jargon and overly technical language
- Use gender-neutral language

## Formatting

- Use Markdown formatting
- Use sentence case for headings
- Use code blocks for code samples
- Use italics for emphasis sparingly
- Use numbered lists for sequential steps
- Use bullet lists for non-sequential items

## Code Examples

- Use syntax highlighting
- Include comments to explain complex code
- Use consistent naming conventions
- Provide context for code samples

## Images

- Use descriptive alt text
- Compress images for faster loading
- Use screenshots sparingly and keep them up-to-date

## Links

- Use descriptive link text (not "click here")
- Check that all links are valid
- Use relative links for internal docs

By following these guidelines, we can create documentation that is clear, consistent, and valuable to our users.
45 changes: 45 additions & 0 deletions docs/show.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,45 @@
# show Documentation

## Brief Description
The `show` method retrieves and displays metadata for a specified model.

## Usage
To use the `show` method, you need to create an instance of the Ollama class and call the `show` method with the required parameters.

```javascript
import Ollama from 'ollama'

const ollama = new Ollama()
```

## Parameters
- `request` (ShowRequest object): An object containing the following properties:
- `model` (string, required): The name of the model to show metadata for.
- `system` (string, optional): A system message to include.
- `template` (string, optional): A template to use for the model.
- `options` (Partial<Options>, optional): Additional options for the model.

## Return Value
The `show` method returns a Promise that resolves to a `ShowResponse` object containing the model's metadata.

## Examples

```javascript
// Basic usage to show metadata for a model
const response = await ollama.show({ model: 'llama2' })
console.log(response)

// Show metadata with additional options
const response = await ollama.show({
model: 'llama2',
system: 'You are a helpful assistant',
template: '{{.System}}\n\nHuman: {{.Prompt}}\n\nAssistant: ',
options: { num_gpu: 1 }
})
console.log(response)
```

## Notes or Considerations
- Ensure that the specified model is available on your Ollama instance before calling the `show` method.
- The `ShowResponse` object includes detailed information about the model, such as its license, modelfile content, parameters, template, system message, and other metadata.
- This method is useful for inspecting model configurations and understanding the capabilities of different models in your Ollama setup.
118 changes: 118 additions & 0 deletions somereadme.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,118 @@
# Dev-Docs: AI-Powered Documentation Generator

## Overview

Dev-Docs is an AI-powered documentation generator designed to streamline the process of creating and maintaining internal documentation for software projects. It integrates seamlessly with Visual Studio Code and offers features like AI-generated context,

![](/img/add_an_image_to_google_slides/step_10.png)

API documentation, and cloud synchronization.

## Key Features

1. AI-powered documentation generation

2. VS Code integration

3. Context generation for multiple files

4. API documentation generation

5. Cloud synchronization

6. Customizable AI prompts

## How It Works

```mermaid
graph TD
A[Install Dev-Docs Extension] --> B[Initialize Dev-Docs]
B --> C[Configure dev-docs.json]
C --> D[Generate Documentation]
D --> E[AI Context Generation]
D --> F[API Documentation]
D --> G[Manual Editing]
E --> H[Sync to Dev-Docs Cloud]
F --> H
G --> H
H --> I[Access on dev-docs.io]
```

## Getting Started

1. Install the Dev-Docs extension in VS Code

2. Initialize Dev-Docs in your project

3. Configure the `dev-docs.json` file

4. Generate documentation using AI or manually

5. Sync your documentation to Dev-Docs Cloud

## Documentation Structure

* Customize Your AI Generation

* Generate Context on Multiple Files

* Generate Context on a Code File

* Generate Context on a Folder

* Generate Documentation with AI

* Intro to Dev-Docs Internal Documentation

* Use VS Code Extension with Continue

* Use AI to Generate API Documentation

* Install the Extension and Create Your First Internal Docs

* Internal Docs Configuration Options

* Sync Your Dev-Docs to Dev-Docs Cloud

## Key Concepts

* **AI Context Generation**: Automatically create context-aware documentation for your codebase

* **API Documentation**: Generate OpenAPI and Postman collections for your APIs

* **Cloud Sync**: Keep your documentation up-to-date across your team by syncing to Dev-Docs Cloud

* **Customizable Prompts**: Tailor AI-generated content to your specific needs

## Configuration

Customize your Dev-Docs experience by editing the `dev-docs.json` file. Example configuration:

```json
{
"quickDoc": {
"acceptedExtensions": [".js", ".py"],
"variablesAndFunctions": {
"prompts": [
{
"question": "Is this a function, class, or variable",
"title": "Code Type",
"documentation": ""
},
{
"question": "Is this code written well? If so why?",
"title": "Quality of Code",
"documentation": ""
}
]
}
},
"ai": {
"onSave": true
}
}
```

## Conclusion

Dev-Docs empowers development teams to create and maintain high-quality internal documentation with minimal effort. By leveraging AI and integrating with popular development tools, Dev-Docs streamlines the documentation process, enabling teams to focus on building great software.