2023-07-19 03:45:38 +08:00
< div align = "center" >
2024-05-02 01:39:38 +08:00
< img alt = "ollama" height = "200px" src = "https://github.com/ollama/ollama/assets/3325447/0d0b44e2-8f4a-4e99-9b52-a5c1c741c8f7" >
2023-07-19 03:45:38 +08:00
< / div >
2023-07-06 03:37:33 +08:00
2023-06-28 00:08:52 +08:00
# Ollama
2023-06-23 00:45:31 +08:00
2023-07-20 03:31:48 +08:00
[](https://discord.gg/ollama)
2023-07-20 03:28:50 +08:00
2024-06-05 04:25:25 +08:00
Get up and running with large language models.
2023-07-20 23:33:28 +08:00
2023-09-26 14:44:53 +08:00
### macOS
2023-08-09 06:50:23 +08:00
2024-02-10 07:19:30 +08:00
[Download ](https://ollama.com/download/Ollama-darwin.zip )
2023-07-19 04:31:25 +08:00
2024-02-16 02:32:40 +08:00
### Windows preview
2023-10-15 14:23:03 +08:00
2024-02-16 02:32:40 +08:00
[Download ](https://ollama.com/download/OllamaSetup.exe )
2023-10-15 14:23:03 +08:00
2024-02-16 02:32:40 +08:00
### Linux
2023-09-26 14:44:53 +08:00
```
2024-02-10 07:19:30 +08:00
curl -fsSL https://ollama.com/install.sh | sh
2023-09-26 14:44:53 +08:00
```
2024-03-27 04:04:17 +08:00
[Manual install instructions ](https://github.com/ollama/ollama/blob/main/docs/linux.md )
2023-09-26 14:44:53 +08:00
2023-10-15 14:23:03 +08:00
### Docker
2023-09-26 14:44:53 +08:00
2023-11-05 03:24:24 +08:00
The official [Ollama Docker image ](https://hub.docker.com/r/ollama/ollama ) `ollama/ollama` is available on Docker Hub.
2023-07-19 04:31:25 +08:00
2024-01-24 08:08:15 +08:00
### Libraries
- [ollama-python ](https://github.com/ollama/ollama-python )
- [ollama-js ](https://github.com/ollama/ollama-js )
2023-07-20 03:28:50 +08:00
## Quickstart
2024-07-29 05:21:38 +08:00
To run and chat with [Llama 3.1 ](https://ollama.com/library/llama3.1 ):
2023-07-20 03:28:50 +08:00
```
2024-07-29 05:21:38 +08:00
ollama run llama3.1
2023-07-20 03:28:50 +08:00
```
## Model library
2024-02-20 09:15:24 +08:00
Ollama supports a list of models available on [ollama.com/library ](https://ollama.com/library 'ollama model library' )
2023-08-17 10:53:27 +08:00
2024-02-20 09:15:24 +08:00
Here are some example models that can be downloaded:
2023-07-20 03:28:50 +08:00
2023-09-26 14:44:53 +08:00
| Model | Parameters | Size | Download |
| ------------------ | ---------- | ----- | ------------------------------ |
2024-07-29 05:21:38 +08:00
| Llama 3.1 | 8B | 4.7GB | `ollama run llama3.1` |
| Llama 3.1 | 70B | 40GB | `ollama run llama3.1:70b` |
| Llama 3.1 | 405B | 231GB | `ollama run llama3.1:405b` |
2024-05-23 00:53:45 +08:00
| Phi 3 Mini | 3.8B | 2.3GB | `ollama run phi3` |
| Phi 3 Medium | 14B | 7.9GB | `ollama run phi3:medium` |
2024-06-28 00:45:16 +08:00
| Gemma 2 | 9B | 5.5GB | `ollama run gemma2` |
| Gemma 2 | 27B | 16GB | `ollama run gemma2:27b` |
2023-12-20 01:59:03 +08:00
| Mistral | 7B | 4.1GB | `ollama run mistral` |
2024-05-23 00:53:45 +08:00
| Moondream 2 | 1.4B | 829MB | `ollama run moondream` |
2023-11-29 11:16:37 +08:00
| Neural Chat | 7B | 4.1GB | `ollama run neural-chat` |
| Starling | 7B | 4.1GB | `ollama run starling-lm` |
2023-09-26 14:44:53 +08:00
| Code Llama | 7B | 3.8GB | `ollama run codellama` |
| Llama 2 Uncensored | 7B | 3.8GB | `ollama run llama2-uncensored` |
2023-12-14 03:38:47 +08:00
| LLaVA | 7B | 4.5GB | `ollama run llava` |
2024-04-16 07:54:23 +08:00
| Solar | 10.7B | 6.1GB | `ollama run solar` |
2023-07-20 03:28:50 +08:00
2024-07-23 04:34:56 +08:00
> [!NOTE]
> You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models.
2023-07-21 03:21:29 +08:00
2023-12-24 00:18:12 +08:00
## Customize a model
2023-06-28 05:13:07 +08:00
2023-10-15 14:23:03 +08:00
### Import from GGUF
2023-09-01 22:54:31 +08:00
2023-10-15 14:23:03 +08:00
Ollama supports importing GGUF models in the Modelfile:
2023-09-01 22:54:31 +08:00
2023-10-15 14:23:03 +08:00
1. Create a file named `Modelfile` , with a `FROM` instruction with the local filepath to the model you want to import.
2023-09-01 22:54:31 +08:00
2023-09-26 14:44:53 +08:00
```
FROM ./vicuna-33b.Q4_0.gguf
```
2023-07-01 00:39:25 +08:00
2023-10-12 07:24:06 +08:00
2. Create the model in Ollama
2023-06-23 00:45:31 +08:00
2023-09-26 14:44:53 +08:00
```
2023-10-15 14:23:03 +08:00
ollama create example -f Modelfile
2023-09-26 14:44:53 +08:00
```
2023-08-10 23:22:28 +08:00
2023-10-12 07:24:06 +08:00
3. Run the model
2023-09-02 04:44:14 +08:00
2023-09-26 14:44:53 +08:00
```
2023-10-15 14:23:03 +08:00
ollama run example
2023-09-26 14:44:53 +08:00
```
2023-09-02 04:44:14 +08:00
2023-10-15 14:23:03 +08:00
### Import from PyTorch or Safetensors
See the [guide ](docs/import.md ) on importing models for more information.
2023-09-26 14:44:53 +08:00
### Customize a prompt
2023-09-02 04:44:14 +08:00
2024-07-29 05:21:38 +08:00
Models from the Ollama library can be customized with a prompt. For example, to customize the `llama3.1` model:
2023-07-20 03:28:50 +08:00
```
2024-07-29 05:21:38 +08:00
ollama pull llama3.1
2023-07-20 03:28:50 +08:00
```
2023-08-09 06:41:48 +08:00
2023-07-19 04:22:33 +08:00
Create a `Modelfile` :
2023-07-06 03:37:33 +08:00
2023-07-01 00:31:00 +08:00
```
2024-07-29 05:21:38 +08:00
FROM llama3.1
2023-07-20 23:17:09 +08:00
# set the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 1
2023-12-13 03:43:19 +08:00
# set the system message
2023-07-20 17:21:51 +08:00
SYSTEM """
2023-07-19 04:32:06 +08:00
You are Mario from Super Mario Bros. Answer as Mario, the assistant, only.
2023-07-19 04:22:33 +08:00
"""
2023-06-30 06:25:02 +08:00
```
2023-07-08 04:14:58 +08:00
2023-07-19 04:22:33 +08:00
Next, create and run the model:
2023-07-08 04:14:58 +08:00
```
2023-07-19 04:22:33 +08:00
ollama create mario -f ./Modelfile
ollama run mario
>>> hi
Hello! It's your friend Mario.
2023-07-08 04:14:58 +08:00
```
2023-10-12 07:24:06 +08:00
For more examples, see the [examples ](examples ) directory. For more information on working with a Modelfile, see the [Modelfile ](docs/modelfile.md ) documentation.
2023-09-26 14:44:53 +08:00
## CLI Reference
### Create a model
`ollama create` is used to create a model from a Modelfile.
2023-07-20 03:28:50 +08:00
2023-12-23 01:10:01 +08:00
```
ollama create mymodel -f ./Modelfile
```
2023-09-26 14:44:53 +08:00
### Pull a model
2023-07-07 04:21:01 +08:00
2023-07-20 03:28:50 +08:00
```
2024-07-29 05:21:38 +08:00
ollama pull llama3.1
2023-07-20 03:28:50 +08:00
```
2023-06-28 21:57:36 +08:00
2023-09-26 14:44:53 +08:00
> This command can also be used to update a local model. Only the diff will be pulled.
### Remove a model
2023-07-21 03:21:29 +08:00
```
2024-07-29 05:21:38 +08:00
ollama rm llama3.1
2023-07-21 03:21:29 +08:00
```
2023-09-26 14:44:53 +08:00
### Copy a model
```
2024-07-29 05:21:38 +08:00
ollama cp llama3.1 my-model
2023-09-26 14:44:53 +08:00
```
### Multiline input
For multiline input, you can wrap text with `"""` :
```
>>> """Hello,
... world!
... """
I'm a basic program that prints the famous "Hello, world!" message to the console.
```
2023-12-14 03:38:47 +08:00
### Multimodal models
```
2024-07-31 09:08:34 +08:00
ollama run llava "What's in this image? /Users/jmorgan/Desktop/smile.png"
2023-12-14 03:38:47 +08:00
The image features a yellow smiley face, which is likely the central focus of the picture.
```
2024-05-02 01:39:38 +08:00
### Pass the prompt as an argument
2023-09-26 14:44:53 +08:00
```
2024-07-29 05:21:38 +08:00
$ ollama run llama3.1 "Summarize this file: $(cat README.md)"
2023-09-26 14:44:53 +08:00
Ollama is a lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications.
```
2024-06-22 06:52:09 +08:00
### Show model information
```
2024-07-29 05:21:38 +08:00
ollama show llama3.1
2024-06-22 06:52:09 +08:00
```
2023-09-26 14:44:53 +08:00
### List models on your computer
2023-07-21 03:21:29 +08:00
2023-09-26 14:44:53 +08:00
```
ollama list
```
2023-07-21 03:21:29 +08:00
2023-09-26 14:44:53 +08:00
### Start Ollama
2023-07-21 03:21:29 +08:00
2023-09-26 14:44:53 +08:00
`ollama serve` is used when you want to start ollama without running the desktop application.
2023-07-21 03:21:29 +08:00
2023-07-04 04:32:48 +08:00
## Building
2024-05-24 05:24:07 +08:00
See the [developer guide ](https://github.com/ollama/ollama/blob/main/docs/development.md )
2023-10-17 08:41:40 +08:00
### Running local builds
2024-02-02 03:16:24 +08:00
2023-08-31 05:54:02 +08:00
Next, start the server:
2023-06-28 01:46:46 +08:00
2023-07-06 03:37:33 +08:00
```
2023-08-31 05:54:02 +08:00
./ollama serve
2023-07-06 03:37:33 +08:00
```
2023-09-01 22:54:31 +08:00
Finally, in a separate shell, run a model:
2023-07-06 03:37:33 +08:00
```
2024-07-29 05:21:38 +08:00
./ollama run llama3.1
2023-07-06 03:37:33 +08:00
```
2023-07-21 15:47:17 +08:00
## REST API
2023-10-27 15:10:23 +08:00
Ollama has a REST API for running and managing models.
2023-12-11 02:53:36 +08:00
### Generate a response
2023-07-21 15:47:17 +08:00
```
2023-11-17 22:50:38 +08:00
curl http://localhost:11434/api/generate -d '{
2024-07-29 05:21:38 +08:00
"model": "llama3.1",
2023-08-09 06:48:47 +08:00
"prompt":"Why is the sky blue?"
}'
2023-07-24 06:01:05 +08:00
```
2023-08-01 04:59:39 +08:00
2023-12-11 02:53:36 +08:00
### Chat with a model
2023-12-06 03:57:33 +08:00
```
curl http://localhost:11434/api/chat -d '{
2024-07-29 05:21:38 +08:00
"model": "llama3.1",
2023-12-08 01:41:56 +08:00
"messages": [
{ "role": "user", "content": "why is the sky blue?" }
2023-12-06 03:57:33 +08:00
]
}'
```
2023-10-27 15:10:23 +08:00
See the [API documentation ](./docs/api.md ) for all endpoints.
2023-09-26 14:44:53 +08:00
## Community Integrations
2023-11-08 16:03:29 +08:00
### Web & Desktop
2024-02-02 03:16:24 +08:00
2024-04-23 08:29:08 +08:00
- [Open WebUI ](https://github.com/open-webui/open-webui )
- [Enchanted (macOS native) ](https://github.com/AugustDev/enchanted )
2024-05-08 04:17:35 +08:00
- [Hollama ](https://github.com/fmaclen/hollama )
2024-04-01 23:16:31 +08:00
- [Lollms-Webui ](https://github.com/ParisNeo/lollms-webui )
2024-03-26 02:59:18 +08:00
- [LibreChat ](https://github.com/danny-avila/LibreChat )
2023-12-16 03:33:04 +08:00
- [Bionic GPT ](https://github.com/bionic-gpt/bionic-gpt )
2023-10-29 05:02:13 +08:00
- [HTML UI ](https://github.com/rtcfirefly/ollama-ui )
2024-03-26 02:54:09 +08:00
- [Saddle ](https://github.com/jikkuatwork/saddle )
2023-10-29 05:18:38 +08:00
- [Chatbot UI ](https://github.com/ivanfioravanti/chatbot-ollama )
2024-04-23 08:09:55 +08:00
- [Chatbot UI v2 ](https://github.com/mckaywrigley/chatbot-ui )
2023-10-29 05:02:13 +08:00
- [Typescript UI ](https://github.com/ollama-interface/Ollama-Gui?tab=readme-ov-file )
2023-10-29 05:18:38 +08:00
- [Minimalistic React UI for Ollama Models ](https://github.com/richawo/minimal-llm-ui )
2023-11-09 03:01:09 +08:00
- [Ollamac ](https://github.com/kevinhermawan/Ollamac )
2024-02-21 14:24:48 +08:00
- [big-AGI ](https://github.com/enricoros/big-AGI/blob/main/docs/config-local-ollama.md )
2023-11-17 00:30:54 +08:00
- [Cheshire Cat assistant framework ](https://github.com/cheshire-cat-ai/core )
2023-11-27 23:44:37 +08:00
- [Amica ](https://github.com/semperai/amica )
2023-11-30 10:18:21 +08:00
- [chatd ](https://github.com/BruceMacD/chatd )
2024-01-02 22:47:50 +08:00
- [Ollama-SwiftUI ](https://github.com/kghandour/Ollama-SwiftUI )
2024-03-26 03:06:39 +08:00
- [Dify.AI ](https://github.com/langgenius/dify )
2024-01-31 23:48:37 +08:00
- [MindMac ](https://mindmac.app )
2024-02-20 10:57:36 +08:00
- [NextJS Web Interface for Ollama ](https://github.com/jakobhoeg/nextjs-ollama-llm-ui )
2024-02-21 03:03:33 +08:00
- [Msty ](https://msty.app )
2024-02-23 20:17:28 +08:00
- [Chatbox ](https://github.com/Bin-Huang/Chatbox )
2024-03-04 16:40:36 +08:00
- [WinForm Ollama Copilot ](https://github.com/tgraupmann/WinForm_Ollama_Copilot )
2024-03-01 04:12:13 +08:00
- [NextChat ](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web ) with [Get Started Doc ](https://docs.nextchat.dev/models/ollama )
2024-03-26 03:00:18 +08:00
- [Alpaca WebUI ](https://github.com/mmo80/alpaca-webui )
2024-03-26 02:58:28 +08:00
- [OllamaGUI ](https://github.com/enoch1118/ollamaGUI )
2024-03-26 02:57:40 +08:00
- [OpenAOE ](https://github.com/InternLM/OpenAOE )
2024-03-07 03:57:49 +08:00
- [Odin Runes ](https://github.com/leonid20000/OdinRunes )
2024-05-07 04:42:16 +08:00
- [LLM-X ](https://github.com/mrdjohnson/llm-x ) (Progressive Web App)
2024-03-26 02:54:48 +08:00
- [AnythingLLM (Docker + MacOs/Windows/Linux native app) ](https://github.com/Mintplex-Labs/anything-llm )
2024-03-26 22:46:36 +08:00
- [Ollama Basic Chat: Uses HyperDiv Reactive UI ](https://github.com/rapidarchitect/ollama_basic_chat )
- [Ollama-chats RPG ](https://github.com/drazdra/ollama-chats )
2024-05-07 04:42:16 +08:00
- [QA-Pilot ](https://github.com/reid41/QA-Pilot ) (Chat with Code Repository)
- [ChatOllama ](https://github.com/sugarforever/chat-ollama ) (Open Source Chatbot based on Ollama with Knowledge Bases)
- [CRAG Ollama Chat ](https://github.com/Nagi-ovo/CRAG-Ollama-Chat ) (Simple Web Search with Corrective RAG)
- [RAGFlow ](https://github.com/infiniflow/ragflow ) (Open-source Retrieval-Augmented Generation engine based on deep document understanding)
- [StreamDeploy ](https://github.com/StreamDeploy-DevRel/streamdeploy-llm-app-scaffold ) (LLM Application Scaffold)
- [chat ](https://github.com/swuecho/chat ) (chat web app for teams)
2024-04-23 08:18:15 +08:00
- [Lobe Chat ](https://github.com/lobehub/lobe-chat ) with [Integrating Doc ](https://lobehub.com/docs/self-hosting/examples/ollama )
2024-05-07 04:42:16 +08:00
- [Ollama RAG Chatbot ](https://github.com/datvodinh/rag-chatbot.git ) (Local Chat with multiple PDFs using Ollama and RAG)
- [BrainSoup ](https://www.nurgo-software.com/products/brainsoup ) (Flexible native client with RAG & multi-agent automation)
2024-05-08 04:31:34 +08:00
- [macai ](https://github.com/Renset/macai ) (macOS client for Ollama, ChatGPT, and other compatible API back-ends)
2024-05-28 08:22:01 +08:00
- [Olpaka ](https://github.com/Otacon/olpaka ) (User-friendly Flutter Web App for Ollama)
2024-05-28 10:58:26 +08:00
- [OllamaSpring ](https://github.com/CrazyNeil/OllamaSpring ) (Ollama Client for macOS)
2024-06-05 05:43:59 +08:00
- [LLocal.in ](https://github.com/kartikm7/llocal ) (Easy to use Electron Desktop Client for Ollama)
2024-07-01 10:00:57 +08:00
- [Ollama with Google Mesop ](https://github.com/rapidarchitect/ollama_mesop/ ) (Mesop Chat Client implementation with Ollama)
2024-07-13 23:33:46 +08:00
- [Kerlig AI ](https://www.kerlig.com/ ) (AI writing assistant for macOS)
2024-07-17 05:24:27 +08:00
- [AI Studio ](https://github.com/MindWorkAI/AI-Studio )
2024-07-18 01:24:44 +08:00
- [Sidellama ](https://github.com/gyopak/sidellama ) (browser-based LLM client)
2024-07-24 02:40:23 +08:00
- [LLMStack ](https://github.com/trypromptly/LLMStack ) (No-code multi-agent framework to build LLM agents and workflows)
2024-04-23 08:18:15 +08:00
2023-11-08 16:03:29 +08:00
### Terminal
2023-11-08 15:52:31 +08:00
2023-10-29 05:02:13 +08:00
- [oterm ](https://github.com/ggozad/oterm )
- [Ellama Emacs client ](https://github.com/s-kostyaev/ellama )
- [Emacs client ](https://github.com/zweifisch/ollama )
2023-11-07 03:27:02 +08:00
- [gen.nvim ](https://github.com/David-Kunz/gen.nvim )
2023-11-14 06:00:17 +08:00
- [ollama.nvim ](https://github.com/nomnivore/ollama.nvim )
2024-03-26 03:06:08 +08:00
- [ollero.nvim ](https://github.com/marco-souza/ollero.nvim )
2024-02-20 10:14:29 +08:00
- [ollama-chat.nvim ](https://github.com/gerazov/ollama-chat.nvim )
2023-11-20 23:39:14 +08:00
- [ogpt.nvim ](https://github.com/huynle/ogpt.nvim )
2023-11-10 04:53:24 +08:00
- [gptel Emacs client ](https://github.com/karthink/gptel )
2023-11-21 19:47:43 +08:00
- [Oatmeal ](https://github.com/dustinblackman/oatmeal )
2023-12-19 11:04:40 +08:00
- [cmdh ](https://github.com/pgibler/cmdh )
2024-03-26 03:08:33 +08:00
- [ooo ](https://github.com/npahlfer/ooo )
2024-04-23 08:10:34 +08:00
- [shell-pilot ](https://github.com/reid41/shell-pilot )
2024-02-20 12:13:03 +08:00
- [tenere ](https://github.com/pythops/tenere )
2024-02-04 07:40:50 +08:00
- [llm-ollama ](https://github.com/taketwo/llm-ollama ) for [Datasette's LLM CLI ](https://llm.datasette.io/en/stable/ ).
2024-03-26 03:05:04 +08:00
- [typechat-cli ](https://github.com/anaisbetts/typechat-cli )
2024-02-20 11:18:05 +08:00
- [ShellOracle ](https://github.com/djcopley/ShellOracle )
2024-03-26 02:53:26 +08:00
- [tlm ](https://github.com/yusufcanb/tlm )
2024-04-23 08:29:08 +08:00
- [podman-ollama ](https://github.com/ericcurtin/podman-ollama )
2024-06-06 05:13:39 +08:00
- [gollama ](https://github.com/sammcj/gollama )
2023-10-29 05:02:13 +08:00
2023-12-12 07:05:10 +08:00
### Database
2024-04-16 06:35:29 +08:00
- [MindsDB ](https://github.com/mindsdb/mindsdb/blob/staging/mindsdb/integrations/handlers/ollama_handler/README.md ) (Connects Ollama models with nearly 200 data platforms and apps)
2024-04-01 23:17:37 +08:00
- [chromem-go ](https://github.com/philippgille/chromem-go/blob/v0.5.0/embed_ollama.go ) with [example ](https://github.com/philippgille/chromem-go/tree/v0.5.0/examples/rag-wikipedia-ollama )
2023-12-13 03:43:19 +08:00
2023-11-21 23:25:32 +08:00
### Package managers
2023-11-21 22:40:59 +08:00
2023-11-21 23:25:26 +08:00
- [Pacman ](https://archlinux.org/packages/extra/x86_64/ollama/ )
2024-02-20 11:05:14 +08:00
- [Helm Chart ](https://artifacthub.io/packages/helm/ollama-helm/ollama )
2024-05-10 02:10:24 +08:00
- [Guix channel ](https://codeberg.org/tusharhero/ollama-guix )
2023-11-21 22:40:59 +08:00
2023-10-29 05:02:13 +08:00
### Libraries
2023-11-08 15:52:31 +08:00
2023-09-26 14:44:53 +08:00
- [LangChain ](https://python.langchain.com/docs/integrations/llms/ollama ) and [LangChain.js ](https://js.langchain.com/docs/modules/model_io/models/llms/integrations/ollama ) with [example ](https://js.langchain.com/docs/use_cases/question_answering/local_retrieval_qa )
2024-07-31 09:40:09 +08:00
- [Firebase Genkit ](https://firebase.google.com/docs/genkit/plugins/ollama )
2023-11-20 23:35:07 +08:00
- [LangChainGo ](https://github.com/tmc/langchaingo/ ) with [example ](https://github.com/tmc/langchaingo/tree/main/examples/ollama-completion-example )
2024-02-23 03:09:08 +08:00
- [LangChain4j ](https://github.com/langchain4j/langchain4j ) with [example ](https://github.com/langchain4j/langchain4j-examples/tree/main/ollama-examples/src/main/java )
2024-06-09 08:29:36 +08:00
- [LangChainRust ](https://github.com/Abraxas-365/langchain-rust ) with [example ](https://github.com/Abraxas-365/langchain-rust/blob/main/examples/llm_ollama.rs )
2023-09-26 14:44:53 +08:00
- [LlamaIndex ](https://gpt-index.readthedocs.io/en/stable/examples/llm/ollama.html )
2023-10-29 05:02:13 +08:00
- [LiteLLM ](https://github.com/BerriAI/litellm )
2023-10-29 05:18:38 +08:00
- [OllamaSharp for .NET ](https://github.com/awaescher/OllamaSharp )
2024-01-07 11:31:39 +08:00
- [Ollama for Ruby ](https://github.com/gbaptista/ollama-ai )
2023-11-05 08:12:18 +08:00
- [Ollama-rs for Rust ](https://github.com/pepperoni21/ollama-rs )
2024-06-12 02:15:05 +08:00
- [Ollama-hpp for C++ ](https://github.com/jmont-dev/ollama-hpp )
2023-11-09 03:04:32 +08:00
- [Ollama4j for Java ](https://github.com/amithkoujalgi/ollama4j )
2023-11-07 03:27:02 +08:00
- [ModelFusion Typescript Library ](https://modelfusion.dev/integration/model-provider/ollama )
2023-11-12 06:41:42 +08:00
- [OllamaKit for Swift ](https://github.com/kevinhermawan/OllamaKit )
2023-11-14 03:50:42 +08:00
- [Ollama for Dart ](https://github.com/breitburg/dart-ollama )
2023-11-20 23:48:35 +08:00
- [Ollama for Laravel ](https://github.com/cloudstudio/ollama-laravel )
2023-12-20 03:04:52 +08:00
- [LangChainDart ](https://github.com/davidmigloz/langchain_dart )
2024-01-12 03:40:23 +08:00
- [Semantic Kernel - Python ](https://github.com/microsoft/semantic-kernel/tree/main/python/semantic_kernel/connectors/ai/ollama )
2024-01-19 05:38:32 +08:00
- [Haystack ](https://github.com/deepset-ai/haystack-integrations/blob/main/integrations/ollama.md )
2024-02-21 03:03:02 +08:00
- [Elixir LangChain ](https://github.com/brainlid/langchain )
2024-01-31 03:56:51 +08:00
- [Ollama for R - rollama ](https://github.com/JBGruber/rollama )
2024-05-08 00:52:30 +08:00
- [Ollama for R - ollama-r ](https://github.com/hauselin/ollama-r )
2024-02-14 03:40:44 +08:00
- [Ollama-ex for Elixir ](https://github.com/lebrunel/ollama-ex )
2024-02-23 02:12:27 +08:00
- [Ollama Connector for SAP ABAP ](https://github.com/b-tocs/abap_btocs_ollama )
2024-03-24 02:55:25 +08:00
- [Testcontainers ](https://testcontainers.com/modules/ollama/ )
2024-05-07 01:25:23 +08:00
- [Portkey ](https://portkey.ai/docs/welcome/integration-guides/ollama )
2024-05-10 00:39:05 +08:00
- [PromptingTools.jl ](https://github.com/svilupp/PromptingTools.jl ) with an [example ](https://svilupp.github.io/PromptingTools.jl/dev/examples/working_with_ollama )
2024-05-12 23:24:21 +08:00
- [LlamaScript ](https://github.com/Project-Llama/llamascript )
2024-06-06 05:13:39 +08:00
2023-11-17 05:46:38 +08:00
### Mobile
2023-12-16 03:37:29 +08:00
- [Enchanted ](https://github.com/AugustDev/enchanted )
2024-01-02 22:47:08 +08:00
- [Maid ](https://github.com/Mobile-Artificial-Intelligence/maid )
2023-11-17 05:46:38 +08:00
2023-11-08 15:52:31 +08:00
### Extensions & Plugins
2023-09-26 14:44:53 +08:00
- [Raycast extension ](https://github.com/MassimilianoPasquini97/raycast_ollama )
- [Discollama ](https://github.com/mxyng/discollama ) (Discord bot inside the Ollama discord channel)
- [Continue ](https://github.com/continuedev/continue )
- [Obsidian Ollama plugin ](https://github.com/hinterdupfinger/obsidian-ollama )
2023-11-08 01:58:13 +08:00
- [Logseq Ollama plugin ](https://github.com/omagdy7/ollama-logseq )
2024-03-04 17:18:10 +08:00
- [NotesOllama ](https://github.com/andersrex/notesollama ) (Apple Notes Ollama plugin)
2023-09-26 14:44:53 +08:00
- [Dagger Chatbot ](https://github.com/samalba/dagger-chatbot )
- [Discord AI Bot ](https://github.com/mekb-turtle/discord-ai-bot )
2023-12-04 03:19:55 +08:00
- [Ollama Telegram Bot ](https://github.com/ruecat/ollama-telegram )
2023-11-08 01:58:13 +08:00
- [Hass Ollama Conversation ](https://github.com/ej52/hass-ollama-conversation )
2023-11-20 23:36:47 +08:00
- [Rivet plugin ](https://github.com/abrenneke/rivet-plugin-ollama )
2023-11-23 03:32:30 +08:00
- [Obsidian BMO Chatbot plugin ](https://github.com/longy2k/obsidian-bmo-chatbot )
2024-03-26 03:07:19 +08:00
- [Cliobot ](https://github.com/herval/cliobot ) (Telegram bot with Ollama support)
2024-02-23 03:17:20 +08:00
- [Copilot for Obsidian plugin ](https://github.com/logancyang/obsidian-copilot )
2024-02-22 23:52:36 +08:00
- [Obsidian Local GPT plugin ](https://github.com/pfrankov/obsidian-local-gpt )
2024-01-24 02:29:10 +08:00
- [Open Interpreter ](https://docs.openinterpreter.com/language-model-setup/local-models/ollama )
2024-05-06 05:45:32 +08:00
- [Llama Coder ](https://github.com/ex3ndr/llama-coder ) (Copilot alternative using Ollama)
- [Ollama Copilot ](https://github.com/bernardo-bruning/ollama-copilot ) (Proxy that allows you to use ollama as a copilot like Github copilot)
2024-01-31 22:25:06 +08:00
- [twinny ](https://github.com/rjmacarthy/twinny ) (Copilot and Copilot chat alternative using Ollama)
2024-07-30 01:53:30 +08:00
- [Wingman-AI ](https://github.com/RussellCanfield/wingman-ai ) (Copilot code and chat alternative using Ollama and Hugging Face)
2024-02-21 03:03:58 +08:00
- [Page Assist ](https://github.com/n4ze3m/page-assist ) (Chrome Extension)
2024-03-26 02:56:42 +08:00
- [AI Telegram Bot ](https://github.com/tusharhero/aitelegrambot ) (Telegram bot using Ollama in backend)
2024-04-01 01:10:05 +08:00
- [AI ST Completion ](https://github.com/yaroslavyaroslav/OpenAI-sublime-text ) (Sublime Text 4 AI assistant plugin with Ollama support)
2024-04-23 08:14:20 +08:00
- [Discord-Ollama Chat Bot ](https://github.com/kevinthedang/discord-ollama ) (Generalized TypeScript Discord Bot w/ Tuning Documentation)
2024-05-17 04:55:14 +08:00
- [Discord AI chat/moderation bot ](https://github.com/rapmd73/Companion ) Chat/moderation bot written in python. Uses Ollama to create personalities.
2024-06-09 09:51:16 +08:00
- [Headless Ollama ](https://github.com/nischalj10/headless-ollama ) (Scripts to automatically install ollama client & models on any OS for apps that depends on ollama server)
2024-04-18 01:48:14 +08:00
2024-06-06 05:13:39 +08:00
### Supported backends
2024-05-06 05:45:32 +08:00
- [llama.cpp ](https://github.com/ggerganov/llama.cpp ) project founded by Georgi Gerganov.
