ollama-chat
Ollama Chat is a conversational AI chat client that uses Ollama to interact with local large language models (LLMs) entirely offline. Ideal for AI enthusiasts, developers, or anyone wanting private, offline LLM chats.
Features
- Chat with local large language models (LLMs) entirely offline
- Prompt Commands to include files, images, and URL content
- Conversation Templates for repeating prompts with variable substitutions
- Browse, download, monitor, and select local models directly in the app
- Multiple concurrent chats
- Show/hide thinking of reasoning models
- Regenerate the most recent conversation response
- Delete the most recent conversation exchange
- View responses as Markdown or text
- Save conversations as Markdown text
- Start a conversation or template from the command line
- Platform independent - tested on macOS, Windows, and Linux
Installation
To get up and running with Ollama Chat follow these steps:
-
Install Ollama
-
Install Ollama Chat
macOS and Linux
python3 -m venv $HOME/venv --upgrade-deps . $HOME/venv/bin/activate pip install ollama-chatWindows
python3 -m venv %USERPROFILE%\venv --upgrade-deps %USERPROFILE%\venv\Scripts\activate pip install ollama-chat
Start Ollama Chat
To start Ollama Chat, open a terminal prompt and follow the steps for your OS. When you start Ollama Chat, a web browser is launched and opens the Ollama Chat application.
By default, a configuration file, "ollama-chat.json", is created in the user's home directory.
macOS and Linux
. $HOME/venv/bin/activate
ollama-chat
Windows
%USERPROFILE%\venv\Scripts\activate
ollama-chat
Start a Conversation from the Command Line
To start a conversation from the command line, use the -m argument:
ollama-chat -m "Why is the sky blue?"
Start a Template from the Command Line
To start a named template from the command line, use the -t and -v arguments:
ollama-chat -t askAristotle -v question "Why is the sky blue?"
Add a Desktop Launcher
To add a desktop launcher, follow the steps for your OS.
macOS
In Finder, locate the "ollama-chat" executable and drag-and-drop it into the lower portion of the Dock.
Windows
In File Explorer, locate the "ollama-chat" executable, right-click it, and select "Pin to Start".
GNOME (Linux)
-
Copy the following Ollama Chat desktop file contents:
[Desktop Entry] Name=Ollama Chat Exec=sh -c "$HOME/venv/bin/ollama-chat" Type=Application Icon=dialog-information Terminal=true Categories=Utility; -
Create the Ollama Chat desktop file and paste the contents:
nano $HOME/.local/share/applications/ollama-chat.desktop -
Update the "Exec" path, if necessary, and save
Conversation Templates
Conversation Templates allow you to repeat a sequence of prompts. Templates can include variable
substitutions in the title text and the prompt text (e.g., {{var}}).
Create a Template
There are two ways to create a template:
- Click "Add Template" from the home page
- Click "Template" on a conversation page
Run a Template
To run a template, click on its title on the home page. If the template has any variables, the user is prompted for their values prior to running the template. When a template runs, a new conversation is created and each prompt is entered in sequence.
Edit a Template
To edit a template, from the home page, click "Select" on the template you want to edit, and then click "Edit". On the template editor page you can update the template's title, set its name, add or remove variables, and add or remove prompts.
Prompt Commands
Ollama Chat supports special prompt commands that allow you to include files, images, and URL content in your prompt, among other things. The following prompt commands are available:
-
/file- include a file/file README.md -
/image- include an image/image image.jpeg -
/dir- include files from a directory/dir src/ollama_chat py -
/url- include a URL resource/url https://craigahobbs.github.io/ollama-chat/README.md -
/do- execute a conversation template by name/do city-report -v CityState "Seattle, WA" -
/?- list available prompt commands/?
To get prompt command help use the -h option:
/file -h
File Format and API Documentation
Development
This package is developed using python-build. It was started using python-template as follows:
template-specialize python-template/template/ ollama-chat/ -k package ollama-chat -k name 'Craig A. Hobbs' -k email 'craigahobbs@gmail.com' -k github 'craigahobbs' -k noapi 1
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ollama_chat-1.1.0.tar.gz.
File metadata
- Download URL: ollama_chat-1.1.0.tar.gz
- Upload date:
- Size: 32.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.14.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e651eba8c488bf6547c2db640ba6c7a796329596778f1a3ccce662602b0b17e0
|
|
| MD5 |
b436fa5216388dd782a8e5cce4bcd7d8
|
|
| BLAKE2b-256 |
9c86b4db5bd58ed94c4eaf1838d42df4a67f0da314d2f5b2b2c36822bedbca70
|
File details
Details for the file ollama_chat-1.1.0-py3-none-any.whl.
File metadata
- Download URL: ollama_chat-1.1.0-py3-none-any.whl
- Upload date:
- Size: 35.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.14.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c0143ea7a931fecd8b31380071d8512d88065fa5c08979328741799ad900c267
|
|
| MD5 |
c29d456aa77115dbd8c05a075416dd8b
|
|
| BLAKE2b-256 |
bf729642c276830613e34f6aff58889fc583561251ef0c6d17a97b05aa753ee8
|
