### Setup Get Requirements

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

A utility function to retrieve project requirements, optionally with a suffix.

```python
def get_requirements(suffix=""):
    
```

--------------------------------

### Base Dockerfile Setup

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history-search-replace-gold.txt

Sets up the base Docker image using Python 3.10 slim. Installs essential build tools, Git, and portaudio, then creates a virtual environment and configures the PATH.

```Dockerfile
FROM python:3.10-slim AS base

RUN apt-get update && \
    apt-get install --no-install-recommends -y build-essential git libportaudio2 && \
    rm -rf /var/lib/apt/lists/*

WORKDIR /app

RUN python -m venv /venv
ENV PATH="/venv/bin:$PATH"
```

```Dockerfile
FROM python:3.10-slim AS base

RUN apt-get update && \
    apt-get install --no-install-recommends -y build-essential git libportaudio2 && \
    rm -rf /var/lib/apt/lists/*

WORKDIR /app

RUN python -m venv /venv
ENV PATH="/venv/bin:$PATH"
ENV AIDER_DOCKER_IMAGE=true
```

--------------------------------

### Install and Run Aider

Source: https://github.com/aider-ai/aider/blob/main/aider/website/index.html

Install Aider using pip and then run it from your project directory. Examples show how to configure different LLM models like DeepSeek, Claude 3.7 Sonnet, and o3-mini.

```bash
python -m pip install aider-install

```

```bash
aider-install

```

```bash
cd /to/your/project

```

```bash
aider --model deepseek --api-key deepseek=<key>

```

```bash
aider --model sonnet --api-key anthropic=<key>

```

```bash
aider --model o3-mini --api-key openai=<key>

```

--------------------------------

### Handy Setup Commands for MacOS/Linux

Source: https://github.com/aider-ai/aider/blob/main/CONTRIBUTING.md

A consolidated command for setting up the development environment on MacOS or Linux systems, including virtual environment creation, activation, and dependency installation.

```bash
python3 -m venv ../aider_venv \
 && source ../aider_venv/bin/activate \
 && pip3 install -e . \
 && pip3 install -r requirements.txt \
 && pip3 install -r requirements/requirements-dev.txt
```

--------------------------------

### Aider Session Initialization Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

This output shows the initial messages when an Aider session starts, including version, model, and repository information. It's useful for verifying Aider's configuration.

```bash
> /Users/gauthier/Projects/aider/.venv/bin/aider --model gpt-4o-mini
> Aider v0.49.0
> Model: gpt-4o-mini with whole edit format
> Git repo: .git with 304 files
> Repo-map: disabled
> Use /help <question> for help, run "aider --help" to see cmd line args
```

--------------------------------

### Pandas Installation Instructions (File Content)

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

This content can be saved to a file to provide pandas installation instructions. It includes commands for both initial installation and upgrading.

```text
To install the Pandas library, you can use pip, which is the package installer for Python. Here’s how you can do it:

1. Open your command line interface (CLI).
2. Run the following command:

pip install pandas

If you want to ensure that you have the latest version, you can use:

pip install --upgrade pandas
```

--------------------------------

### Run Installation Command

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Executes a given command for installation.

```python
def run_install(cmd):
⋮...
```

--------------------------------

### Aider Command Line Usage

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Example of how to start Aider with a specific model and the command to run for help.

```bash
/Users/gauthier/Projects/aider/.venv/bin/aider --model gpt-4o-mini
```

```bash
/help how are you
```

--------------------------------

### Aider Command Line Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Example of launching Aider from the command line with specific model and repository information.

```text
> /Users/gauthier/Projects/aider/.venv/bin/aider --model gpt-4o-mini  
> Aider v0.48.2-dev  
> Model: gpt-4o-mini with whole edit format  
> Git repo: .git with 303 files  
> Repo-map: disabled  
> Use /help <question> for help, run "aider --help" to see cmd line args
```

--------------------------------

### Install Project Dependencies

Source: https://github.com/aider-ai/aider/blob/main/CONTRIBUTING.md

Install the project's main dependencies from the `requirements.txt` file.

```bash
pip install -r requirements.txt
```

--------------------------------

### Add Installation Section to Markdown

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/usage/not-code.md

Add an installation section to a README.md file with options for Homebrew and PyPI.

```markdown
+ ## Installation
+ ```
+ # Homebrew
+ brew install cool-app-10k
+ 
+ # PyPI
+ pipx install cool-app-10k
+ ```
```

--------------------------------

### Aider Command Line Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Example of launching Aider from the command line, including the model used and git repository information.

```bash
/Users/gauthier/Projects/aider/.venv/bin/aider --model gpt-4o-mini
Aider v0.48.0
Model: gpt-4o-mini with whole edit format
Git repo: .git with 300 files
Repo-map: disabled
Use /help <question> for help, run "aider --help" to see cmd line args
```

--------------------------------

### Start Aider with OpenAI Models

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/llms/openai.md

Launch Aider and specify the desired OpenAI model using the --model flag. Examples include o3-mini, o1-mini, and gpt-4o.

```bash
# Change directory into your codebase
cd /to/your/project

# o3-mini
aider --model o3-mini

# o1-mini
aider --model o1-mini

# GPT-4o
aider --model gpt-4o

# List models available from OpenAI
aider --list-models openai/
```

--------------------------------

### Aider Startup Announcement Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

This is an example of the announcement lines aider prints at startup, which are helpful for reporting problems.

```text
Aider v0.37.1-dev
Models: gpt-4o with diff edit format, weak model gpt-3.5-turbo
Git repo: .git with 258 files
Repo-map: using 1024 tokens
```

--------------------------------

### Test Main Setup Method

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

The setUp method for the TestMain class, which copies the original environment variables before each test.

```python
def setUp(self):
        self.original_env = os.environ.copy()

```

--------------------------------

### Aider Ask Command Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Example of using the `/ask` command to inquire about the repository, with Aider providing a descriptive answer.

```markdown
/ask What is this repo?

This is the source code to the popular django package.
```

--------------------------------

### Example of using /code command

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

This example demonstrates how to use the `/code` command to request a specific code change, such as adding a factorial function.

```markdown
#### /code Add a function to calculate the factorial of a number

Certainly! I'll add a function to calculate the factorial of a number. Here's the change:

```python
def factorial(n):
    if n == 0 or n == 1:
        return 1
    else:
        return n * factorial(n - 1)

```
```

--------------------------------

### Install Pre-commit Hooks

Source: https://github.com/aider-ai/aider/blob/main/CONTRIBUTING.md

Install pre-commit hooks to automatically format code and run linters before each commit. This is optional but recommended.

```bash
pre-commit install
```

--------------------------------

### Install and Run Aider CLI

Source: https://github.com/aider-ai/aider/blob/main/README.md

Install Aider using pip and run it from the command line. Remember to change directory into your project before running Aider.

```bash
python -m pip install aider-install

```

```bash
aider-install

```

```bash
cd /to/your/project

```

```bash
# DeepSeek

```

```bash
aider --model deepseek --api-key deepseek=<key>

```

```bash
# Claude 3.7 Sonnet

```

```bash
aider --model sonnet --api-key anthropic=<key>

```

```bash
# o3-mini

```

```bash
aider --model o3-mini --api-key openai=<key>

```

--------------------------------

### Aider Configuration File Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Configuration settings for Aider can be managed in a YAML file. This example shows the `lint-cmd` and `cache-prompts` settings.

```yaml
lint-cmd:          /Users/gauthier/Projects/aider/tmp.lint.sh
cache-prompts:     true
```

--------------------------------

### Setup for Aider Benchmarking

Source: https://github.com/aider-ai/aider/blob/main/benchmark/README.md

Clone the Aider repository, set up the benchmark exercises directory, and build the Docker container. These steps are required once before running benchmarks.

```bash
# Clone the aider repo
git clone https://github.com/Aider-AI/aider.git

# Create the scratch dir to hold benchmarking results inside the main aider dir:
cd aider
mkdir tmp.benchmarks

# Clone the repo with the exercises
git clone https://github.com/Aider-AI/polyglot-benchmark tmp.benchmarks/polyglot-benchmark

# Build the docker container
./benchmark/docker_build.sh
```

--------------------------------

### Get All Tags Since

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Retrieves all Git tags created since a specified starting tag.

```python
def get_all_tags_since(start_tag):

```

--------------------------------

### Test Main Setup Method

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Sets up the testing environment for the main command tests, including environment variables and temporary directories.

```python
def setUp(self):
        self.original_env = os.environ.copy()
        os.environ["OPENAI_API_KEY"] = "deadbeef"
        self.original_cwd = os.getcwd()
        self.tempdir_obj = IgnorantTemporaryDirectory()
        self.tempdir = self.tempdir_obj.name

```

--------------------------------

### TestMain Setup Method

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Sets up the testing environment for TestMain, including copying environment variables, setting a temporary directory, and creating dummy files.

```python
class TestMain(TestCase):
    def setUp(self):
        self.original_env = os.environ.copy()
        os.environ["OPENAI_API_KEY"] = "deadbeef"
        self.original_cwd = os.getcwd()
        self.tempdir_obj = IgnorantTemporaryDirectory()
        self.tempdir = self.tempdir_obj.name

```

```python
    def create_env_file(self, file_name, content):

```

--------------------------------

### Version Control Get All Tags Since

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Retrieves all Git tags that have been created since a specified start tag.

```python
def get_all_tags_since(start_tag):
    
```

--------------------------------

### Example Pip Install Conflict Message

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/troubleshooting/imports.md

This message indicates a version conflict between Aider's requirements and your current environment. It suggests that a package required by Aider has a specific version constraint that is not met by the version you currently have installed.

```text
aider-chat 0.23.0 requires somepackage==X.Y.Z, but you have somepackage U.W.V which is incompatible.
```

--------------------------------

### Example with Tagged Multi-line Message

Source: https://github.com/aider-ai/aider/blob/main/aider/website/_includes/multi-line.md

Use a tag to start and end a multi-line message, which is useful when your message content includes closing braces.

```markdown
{python
def hello():
    print("Hello}")  # Note: contains a brace
python}
```

--------------------------------

### Get User Language using Babel library

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Leverages the `babel` library for more robust locale and language detection. Requires installing the `babel` dependency.

```python
from babel import Locale

def get_user_language():
    return Locale.parse(locale.getdefaultlocale()[0]).language
```

--------------------------------

### Complete Example: Responsive Chart Implementation

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

This comprehensive example integrates HTML structure, CSS for small screens, Chart.js configuration, and a resize listener for a fully responsive chart.

```html
<style>
    @media (max-width: 600px) {
        .chart-container {
            width: 100%;
            padding-bottom: 100%;
            position: relative;
        }
        .chart-container canvas {
            position: absolute;
            top: 0;
            left: 0;
            right: 0;
            bottom: 0;
            width: 100% !important;
            height: 100% !important;
        }
    }
</style>

<div class="chart-container" style="position: relative; width: 100%; max-width: 800px; margin: 0 auto;">
    <canvas id="passRateChart" style="margin-bottom: 20px"></canvas>
</div>

<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
<script>
document.addEventListener('DOMContentLoaded', function () {
    var ctx = document.getElementById('passRateChart').getContext('2d');
    
    // ... (your existing code for data preparation)

    var config = {
        type: 'bar',
        data: data,
        options: {
            responsive: true,
            maintainAspectRatio: true,
            aspectRatio: 2,
            scales: {
                // ... (your existing scales configuration)
            },
            plugins: {
                // ... (your existing plugins configuration)
            }
        },
        plugins: [
            // ... (your existing plugins)
        ]
    };

    var chart = new Chart(ctx, config);

    window.addEventListener('resize', function() {
        chart.resize();
    });
});

// ... (rest of your existing code)
</script>
```

--------------------------------

### Aider Session Exit Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

This output indicates the start of an Aider chat session, including the command used and version information. It's helpful for tracking session history.

```bash
> /Users/gauthier/Projects/aider/.venv/bin/aider --model gpt-4o-mini
> Aider v0.48.2-dev
> Model: gpt-4o-mini with whole edit format
> Git repo: .git with 303 files
> Repo-map: disabled
> Use /help <question> for help, run "aider --help" to see cmd line args
```

--------------------------------

### Initial Instruction for GPT

Source: https://github.com/aider-ai/aider/blob/main/aider/website/_posts/2023-07-02-benchmarks.md

This is the initial instruction sent to GPT to start an exercise. It guides GPT to use provided instructions, implement stubs, and only use standard Python libraries.

```text
Use the above instructions to modify the supplied files: <implementation file>
Keep and implement the existing function or class stubs, they will be called from unit tests.
Only use standard python libraries, don't suggest installing any packages.
```

--------------------------------

### Initial Plotting Setup in benchmark/over_time.py

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Sets up the initial plotting environment by loading data from a YAML file and initializing lists for dates, pass rates, and models.

```python
def plot_over_time(yaml_file):
    with open(yaml_file, "r") as file:
        data = yaml.safe_load(file)

    dates = []
    pass_rates = []
    models = []

```

--------------------------------

### Aider Initialization and Commit Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Illustrates the initialization of an Aider chat session with specific configurations and a commit command.

```bash
/Users/gauthier/Projects/aider/.venv/bin/aider --lint --commit
Aider v0.51.2-dev
Main model: claude-3-5-sonnet-20240620 with diff edit format, prompt cache, infinite output
Weak model: claude-3-haiku-20240307
Git repo: .git with 308 files
Repo-map: using 1024 tokens, files refresh
Commit b2488af fix: Handle path-specific edits in base_coder.py
test: Update test_main.py to check for explicit approval of shell commands
```

--------------------------------

### Get Author Line Counts for File

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Calculates the number of lines authored by each person in a given file. Handles cases where the file might not exist at the start tag but exists at the end tag or HEAD.

```python
def get_counts_for_file(repo, tag, file_path):
    try:
        # Get blame for the file at the given tag
        blame_output = repo.git.blame(f'{tag}', '--', file_path)
        # Parse blame output to extract author information
        authors = {}
        for line in blame_output.splitlines():
            parts = line.split(' ', 2)
            if len(parts) == 3:
                hash_val, author_info, _ = parts
                # Extract author name from author_info (e.g., 'John Doe <john.doe@example.com>')
                author_name = author_info.split('<')[0].strip()
                authors[hash_val] = author_name

        # Get the content of the file at the given tag
        text = repo.git.show(f'{tag}:{file_path}')
        if text is None:
            # File doesn't exist at the tag, try HEAD
            text = repo.git.show(f'HEAD:{file_path}')
            if text is None:
                return None

        text = text.splitlines()
        line_counts = defaultdict(int)
        for line in text:
            if line.startswith("^ "):
                continue
            hsh = line[:hash_len]
            author = authors.get(hsh, "Unknown")
            line_counts[author] += 1
        return dict(line_counts)
    except subprocess.CalledProcessError:
        # File doesn't exist at all
        return None
```

--------------------------------

### Get Line Counts Per Author for a File (Python)

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history-search-replace-gold.txt

Calculates the number of lines authored by each person in a given file between two Git tags. Handles cases where the file might not exist at the start tag.

```python
def get_counts_for_file(start_tag, end_tag, authors, fname):
    try:
        if end_tag:
            text = run(["git", "blame", f"{start_tag}..{end_tag}", "--", fname])
        else:
            text = run(["git", "blame", f"{start_tag}..HEAD", "--", fname])
        if not text:
            return None
        text = text.splitlines()
        line_counts = defaultdict(int)
        for line in text:
            if line.startswith("^"):
                continue
            hsh = line[:hash_len]
            author = authors.get(hsh, "Unknown")
            line_counts[author] += 1

        return dict(line_counts)
    except subprocess.CalledProcessError:
        # File might not exist at start_tag or end_tag
        return None
```

```python
def get_counts_for_file(start_tag, end_tag, authors, fname):
    try:
        if end_tag:
            text = run(["git", "blame", f"{start_tag}..{end_tag}", "--", fname])
        else:
            text = run(["git", "blame", f"{start_tag}..HEAD", "--", fname])
        if not text:
            return None
        text = text.splitlines()
        line_counts = defaultdict(int)
        for line in text:
            if line.startswith("^"):
                continue
            hsh = line[:hash_len]
            author = authors.get(hsh, "Unknown")
            line_counts[author] += 1

        return dict(line_counts)
    except subprocess.CalledProcessError:
        # File might not exist at start_tag or end_tag, or might have been renamed
        # Try to get the blame for the entire file at the end_tag (or HEAD)
        try:
            if end_tag:
                text = run(["git", "blame", end_tag, "--", fname])
            else:
                text = run(["git", "blame", "HEAD", "--", fname])
            if not text:
                return None
            text = text.splitlines()
            line_counts = defaultdict(int)
            for line in text:
                if line.startswith("^"):
                    continue
                hsh = line[:hash_len]
                author = authors.get(hsh, "Unknown")
                line_counts[author] += 1
            return dict(line_counts)
        except subprocess.CalledProcessError:
            # File doesn't exist at all
            return None
```

--------------------------------

### Asynchronous IO and Coder for Web Integration

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

This example demonstrates an asynchronous IO class and a Coder class designed for web UI or API integration. It uses asyncio queues for managing user input and responses, and includes a basic FastAPI setup with websockets for real-time communication.

```python
import asyncio
from enum import Enum

class State(Enum):
    IDLE = 0
    WAITING_FOR_INPUT = 1
    PROCESSING = 2

class WebIO:
    def __init__(self):
        self.state = State.IDLE
        self.pending_questions = asyncio.Queue()
        self.answers = asyncio.Queue()

    async def ask_user(self, question):
        await self.pending_questions.put(question)
        self.state = State.WAITING_FOR_INPUT
        return await self.answers.get()

    async def user_response(self, answer):
        await self.answers.put(answer)
        self.state = State.PROCESSING

class AsyncCoder:
    def __init__(self, io):
        self.io = io

    async def run(self):
        while True:
            if self.io.state == State.IDLE:
                # Process next task
                await self.process_next_task()
            elif self.io.state == State.WAITING_FOR_INPUT:
                # Wait for user input
                await asyncio.sleep(0.1)
            elif self.io.state == State.PROCESSING:
                # Continue processing
                await self.continue_processing()

    async def process_next_task(self):
        # Your processing logic here
        question = "Do you want to proceed?"
        answer = await self.io.ask_user(question)
        # Handle the answer

    async def continue_processing(self):
        # Continue processing logic here
        pass

# For web framework integration (e.g., FastAPI)
from fastapi import FastAPI, WebSocket

app = FastAPI()
io = WebIO()
coder = AsyncCoder(io)

@app.websocket("/ws")
async def websocket_endpoint(websocket: WebSocket):
    await websocket.accept()
    asyncio.create_task(coder.run())
    while True:
        if not io.pending_questions.empty():
            question = await io.pending_questions.get()
            await websocket.send_text(question)
        
        data = await websocket.receive_text()
        await io.user_response(data)
```

--------------------------------

### Install and Launch Aider in Browser Mode

Source: https://github.com/aider-ai/aider/blob/main/aider/website/_posts/2024-05-02-browser.md

Install Aider using pip and set your OpenAI API key. Then, launch Aider with the --browser flag to use the experimental browser UI.

```bash
python -m pip install -U aider-chat

export OPENAI_API_KEY=<key> # Mac/Linux
setx   OPENAI_API_KEY <key> # Windows, restart shell after setx


aider --browser
```

--------------------------------

### Ask/Code Workflow Example

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/usage/modes.md

Demonstrates a recommended workflow using '/ask' for discussion and planning, followed by '/code' for file edits. The example shows iterative refinement of a print statement in a Python file.

```python
hello.py
>>>>>>> SEARCH
=======
def main():
    print("I think, therefore I print.")
<<<<<<< REPLACE
```

```python
hello.py
>>>>>>> SEARCH
    print("I think, therefore I print.")
=======
    print("I THINK, THEREFORE I PRINT!")
<<<<<<< REPLACE
```

--------------------------------

### Install Aider CLI using aider-install package

Source: https://github.com/aider-ai/aider/blob/main/aider/website/_posts/2025-01-15-uv.md

For users with Python 3.8+ installed, this method installs the `aider-install` package, which then uses uv to install the Aider CLI and manage its environment.

```bash
pip install aider-install
aider-install
```

--------------------------------

### Check Pip Install Extra

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Checks if an extra module is installed via pip and prompts for installation if not.

```python
def check_pip_install_extra(io, module, prompt, pip_install_cmd):
⋮...
```

--------------------------------

### Aider Quick Start with Copilot

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/llms/github.md

Navigate to your project directory and run Aider, specifying a Copilot model like `openai/gpt-4o` to begin interacting with Copilot through Aider.

```bash
# change into your project
cd /to/your/project

# talk to Copilot
aider --model openai/gpt-4o
```

--------------------------------

### Install Pandas Package

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history-search-replace-gold.txt

Use this shell command to install the pandas library. This is a basic installation command.

```shell
pip install pandas
```

--------------------------------

### Install Aider

Source: https://github.com/aider-ai/aider/blob/main/aider/website/_includes/get-started.md

Install aider using the provided include file. Ensure you have Python 3.8-3.13 installed.

```bash
{% include install.md %}
```

--------------------------------

### Aider Help Command Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Demonstrates using the `/help` command in Aider to ask questions about its usage, configuration, or troubleshooting.

```bash
/help how are you
```

--------------------------------

### Playwright Installation

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Installs Playwright dependencies.

```python
│def install_playwright(io):
⋮...
```

--------------------------------

### Aider's install script snippet for installing aider as a tool

Source: https://github.com/aider-ai/aider/blob/main/aider/website/_posts/2025-01-15-uv.md

This snippet from Aider's install script demonstrates how uv is used to install the `aider-chat` tool, specifying Python 3.12 and using the --force option.

```bash
ensure "${_install_dir}/uv" tool install --force --python python3.12 aider-chat@latest
```

--------------------------------

### Start Ollama Server and Aider

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/llms/ollama.md

Instructions for pulling an Ollama model, starting the Ollama server with an increased context window, and then running Aider against the local model.

```bash
# Pull the model
ollama pull <model>
```

```bash
# Start your ollama server, increasing the context window to 8k tokens
OLLAMA_CONTEXT_LENGTH=8192 ollama serve
```

```bash
# In another terminal window, change directory into your codebase
cd /to/your/project


```

```bash
aider --model ollama_chat/<model>
```

--------------------------------

### Install Aider CLI with uv tool install

Source: https://github.com/aider-ai/aider/blob/main/aider/website/_posts/2025-01-15-uv.md

This command, executed by `aider-install`, uses uv to globally install the `aider-chat` tool, ensuring it runs with Python 3.12. The --force flag is used to overwrite existing installations.

```bash
uv tool install --force --python python3.12 aider-chat
```

--------------------------------

### Create Flask App with /hello Endpoint

Source: https://github.com/aider-ai/aider/blob/main/aider/website/examples/hello-world-flask.md

This snippet initializes a Flask application and defines a '/hello' endpoint that returns 'Hello, World!'. Ensure Flask is installed (`pip install flask`) before running.

```python
from flask import Flask

app = Flask(__name__)

@app.route('/hello')
def hello():
    return "Hello, World!"

if __name__ == '__main__':
    app.run()
```

--------------------------------

### Verify Pandas Installation

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

After installation, run this Python code to confirm pandas is installed and to check its version. This requires an active Python interpreter.

```python
import pandas as pd
print(pd.__version__)
```

--------------------------------

### Install Aider with pip

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/install.md

Install aider using pip. It is recommended to use a virtual environment when installing with pip to manage dependencies effectively.

```bash
python -m pip install -U --upgrade-strategy only-if-needed aider-chat
```

--------------------------------

### Install Aider with pipx

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/install.md

Install aider using the pipx package manager. This command also installs pipx if it's not already present.

```bash
python -m pip install pipx  # If you need to install pipx
```

```bash
pipx install aider-chat
```

--------------------------------

### Initialize Repository Mapping and Tag Ranking

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history-search-replace-gold.txt

Sets up data structures for defines, references, and definitions, and initializes personalization for graph analysis. Handles large repositories with a progress bar.

```python
    def get_ranked_tags(
        self,
        chat_fnames,
        other_fnames,
        mentioned_fnames,
        mentioned_idents,
        progress=None,
    ):
        import networkx as nx

        defines = defaultdict(set)
        references = defaultdict(list)
        definitions = defaultdict(set)

        personalization = dict()

        fnames = set(chat_fnames).union(set(other_fnames))
        chat_rel_fnames = set()

        fnames = sorted(fnames)

        # Default personalization for unspecified files is 1/num_nodes
        # https://networkx.org/documentation/stable/_modules/networkx/algorithms/link_analysis/pagerank_alg.html#pagerank
        personalize = 100 / len(fnames)

        if len(fnames) - len(self.TAGS_CACHE) > 100:
            self.io.tool_output(
                "Initial repo scan can be slow in larger repos, but only happens once."
            )
            fnames = tqdm(fnames, desc="Scanning repo")
            showing_bar = True
        else:
            showing_bar = False

        for fname in fnames:
            if progress and not showing_bar:
                progress()

            self.process_file(
                fname,
                chat_fnames,
                mentioned_fnames,
                personalize,
                defines,
                references,
                definitions,
                personalization,
                chat_rel_fnames,
            )

        if not references:
            references = dict((k, list(v)) for k, v in defines.items())

        idents = set(defines.keys()).intersection(set(references.keys()))

        G = nx.MultiDiGraph()
```

```python
    def get_ranked_tags(
        self,
        chat_fnames,
        other_fnames,
        mentioned_fnames,
        mentioned_idents,
        progress=None,
    ):
        import networkx as nx
        from collections import Counter
        import math

        defines = defaultdict(set)
        references = defaultdict(list)
        definitions = defaultdict(set)

        personalization = dict()

        fnames = set(chat_fnames).union(set(other_fnames))
        chat_rel_fnames = set()

        fnames = sorted(fnames)

        # Default personalization for unspecified files is 1/num_nodes
        # https://networkx.org/documentation/stable/_modules/networkx/algorithms/link_analysis/pagerank_alg.html#pagerank
        personalize = 100 / len(fnames)

        if len(fnames) - len(self.TAGS_CACHE) > 100:
            self.io.tool_output(
                "Initial repo scan can be slow in larger repos, but only happens once."
            )
            fnames = tqdm(fnames, desc="Scanning repo")
            showing_bar = True
        else:
            showing_bar = False

        for fname in fnames:
            if progress and not showing_bar:
                progress()

            self.process_file(
                fname,
                chat_fnames,
                mentioned_fnames,
                personalize,
                defines,
                references,
                definitions,
                personalization,
                chat_rel_fnames,
            )

        if not references:
            references = dict((k, list(v)) for k, v in defines.items())

```

--------------------------------

### Configure o3-mini Model Settings

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/config/reasoning.md

Example configuration for the 'o3-mini' model, demonstrating how to set `use_temperature` to `false` which is often required for reasoning models.

```yaml
- name: o3-mini
  edit_format: diff
  weak_model_name: gpt-4o-mini
  use_repo_map: true
  use_temperature: false             # <--- 
  editor_model_name: gpt-4o
  editor_edit_format: editor-diff
  accepts_settings: ["reasoning_effort"]

```

--------------------------------

### Install Aider with PowerShell (Windows)

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/install.md

Execute the aider installation script on Windows using PowerShell. This command bypasses execution policy restrictions for the installation.

```powershell
powershell -ExecutionPolicy ByPass -c "irm https://aider.chat/install.ps1 | iex"
```

--------------------------------

### Install Aider in Docker Image

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history-search-replace-gold.txt

Installs Aider and its dependencies, including PyTorch CPU version, into the Docker image. Cleans up the source code directory after installation.

```Dockerfile
COPY . /tmp/aider
RUN /venv/bin/python -m pip install --upgrade --no-cache-dir pip \
    && /venv/bin/python -m pip install --no-cache-dir /tmp/aider[help,browser,playwright] \
       --extra-index-url https://download.pytorch.org/whl/cpu \
    && rm -rf /tmp/aider
```

```Dockerfile
COPY . /tmp/aider
RUN /venv/bin/python -m pip install --upgrade --no-cache-dir pip \
    && /venv/bin/python -m pip install --no-cache-dir /tmp/aider \
       --extra-index-url https://download.pytorch.org/whl/cpu \
    && rm -rf /tmp/aider
```

```Dockerfile
COPY . /tmp/aider
RUN /venv/bin/python -m pip install --upgrade --no-cache-dir pip \
    && /venv/bin/python -m pip install --no-cache-dir /tmp/aider \
       --extra-index-url https://download.pytorch.org/whl/cpu \
    && rm -rf /tmp/aider
```

```Dockerfile
COPY . /tmp/aider
RUN /venv/bin/python -m pip install --upgrade --no-cache-dir pip \
    && /venv/bin/python -m pip install --no-cache-dir /tmp/aider \
       --extra-index-url https://download.pytorch.org/whl/cpu \
    && rm -rf /tmp/aider
```

--------------------------------

### Install Aider and Configure Models

Source: https://github.com/aider-ai/aider/blob/main/aider/website/_posts/2024-07-25-new-models.md

Install the aider package and set environment variables for API keys. Then, use the aider command with the --model flag to specify the desired LLM.

```bash
python -m pip install -U aider-chat
```

```bash
cd /to/your/git/repo
```

```bash
export DEEPSEEK_API_KEY=your-key-goes-here
aider --model deepseek/deepseek-coder
```

```bash
export MISTRAL_API_KEY=your-key-goes-here
aider --model mistral/mistral-large-2407
```

```bash
export OPENROUTER_API_KEY=your-key-goes-here
aider --model openrouter/meta-llama/llama-3.1-405b-instruct
```

```bash
aider --model openrouter/meta-llama/llama-3.1-70b-instruct
```

```bash
aider --model openrouter/meta-llama/llama-3.1-8b-instruct
```

--------------------------------

### Start Aider with LM Studio Model

Source: https://github.com/aider-ai/aider/blob/main/aider/website/docs/llms/lm-studio.md

After configuring the environment variables, use this command to start Aider and specify the LM Studio model you want to use.

```bash
# Change directory into your codebase
cd /to/your/project

aider --model lm_studio/<your-model-name>
```

--------------------------------

### Install Playwright

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Installs Playwright, a tool for web browser automation.

```python
def install_playwright(io):
⋮...
```

--------------------------------

### Aider Help Command Example

Source: https://github.com/aider-ai/aider/blob/main/tests/fixtures/chat-history.md

Demonstrates how to use the `/help` command within Aider to ask questions about its usage, settings, or troubleshooting.

```text
# Question:  how are you

# Relevant docs:
```