Skip to main content

Oai2Ollama

This is a CLI tool that starts a server that wraps an OpenAI-compatible API and expose an Ollama-compatible API, which is useful for providing custom models for coding agents that don't support custom OpenAI APIs but do support Ollama (like GitHub Copilot for VS Code).

Usage

with Python

You can run directly via uvx (if you have uv installed) or pipx:

uvx oai2ollama --help
usage: oai2ollama [--api-key str] [--base-url HttpUrl] [--capabilities list[str]] [--models list[str]] [--host str]
options:
  --help, -h                    Show this help message and exit
  --api-key str                 API key for authentication (required)
  --base-url HttpUrl            Base URL for the OpenAI-compatible API (required)
  --capabilities, -c list[str]  Extra capabilities to mark the model as supporting
  --models, -m list[str]        Extra models to include in the /api/tags response
  --host str                    IP / hostname for the API server (default: localhost)

To mark the model as supporting certain capabilities, you can use the --capabilities (or -c) option with a list of strings. For example, the following two syntaxes are supported:

oai2ollama -c tools or oai2ollama --capabilities tools

oai2ollama -c tools -c vision or oai2ollama --capabilities -c tools,vision

To support models that are not returned by the /models endpoint, use the --models (or -m) option to add them to the /api/tags response:

oai2ollama -m model1 -m model2 or oai2ollama -m model1,model2

Capabilities currently used by Ollama are: tools, insert, vision, embedding, thinking and completion. We always include completion.

Or you can use a .env file to set these options:

OPENAI_API_KEY=your_api_key
OPENAI_BASE_URL=your_base_url
HOST=0.0.0.0
CAPABILITIES=["vision","thinking"]
MODELS=["custom-model1","custom-model2"]

The option name capacities is deprecated. Use capabilities instead. The old name still works for now but will emit a deprecation warning.

with Docker

First, build the image:

docker build -t oai2ollama .

Then, run the container with your credentials:

docker run -p 11434:11434 \
  -e OPENAI_API_KEY="your_api_key" \
  -e OPENAI_BASE_URL="your_base_url" \
  oai2ollama

Or you can pass these as command line arguments:

docker run -p 11434:11434 oai2ollama --api-key your_api_key --base-url your_base_url

To have the server listen on a different host, like all IPv6 interfaces, use the --host argument:

docker run -p 11434:11434 oai2ollama --host "::"

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

oai2ollama-1.2.8.4.tar.gz (3.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

oai2ollama-1.2.8.4-py3-none-any.whl (5.1 kB view details)

Uploaded Python 3

File details

Details for the file oai2ollama-1.2.8.4.tar.gz.

File metadata

  • Download URL: oai2ollama-1.2.8.4.tar.gz
  • Upload date:
  • Size: 3.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for oai2ollama-1.2.8.4.tar.gz
Algorithm Hash digest
SHA256 045b4dabe403e6bb8731b78adf301d929bf49d6c63684152ac938affca9e66b4
MD5 fccca35f121d969414cf686782650fc8
BLAKE2b-256 cd739fcb79705961afbd2677b27d05977c71d7a5ca73f64fbd4ee440dd56f2f9

See more details on using hashes here.

Provenance

The following attestation bundles were made for oai2ollama-1.2.8.4.tar.gz:

Publisher: ci.yml on CNSeniorious000/oai2ollama

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file oai2ollama-1.2.8.4-py3-none-any.whl.

File metadata

  • Download URL: oai2ollama-1.2.8.4-py3-none-any.whl
  • Upload date:
  • Size: 5.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for oai2ollama-1.2.8.4-py3-none-any.whl
Algorithm Hash digest
SHA256 40f316222208847246f30dfc9fe8710f0feab171ed7d73dbd3e1897610e56db5
MD5 248ee457e931a245da4b3f7af7f4c1c3
BLAKE2b-256 253bceca5b758584934ea9f6d9f4e17b98a129cc08295fe72b9e58212f2f4076

See more details on using hashes here.

Provenance

The following attestation bundles were made for oai2ollama-1.2.8.4-py3-none-any.whl:

Publisher: ci.yml on CNSeniorious000/oai2ollama

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

1.2.8.4 This release

2 files

1.2.8.3

2 files

1.2.8.2

2 files

1.2.8.1

1 file

1.2.8

1 file

1.2.7

2 files

1.2.6

2 files

1.2.5

2 files

1.2.4

2 files

1.2.3

2 files

1.2.2

2 files

1.2.1

2 files

1.2.0

2 files

1.1.0

2 files

1.0.8

2 files

1.0.7

2 files

1.0.6

2 files

1.0.5

2 files

1.0.4

2 files

1.0.3

2 files

1.0.2

2 files

1.0.1

2 files

1

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page