Skip to main content

Lime is the MaaS proxy for anonymously access with OpenAI API.

Project description

Lime

Lime is the MaaS proxy for anonymously access with OpenAI API.

  • Compatible with multiple OpenAI API endpoints.
  • Allow anonymous access for unregistered users.
  • Configurable for free MaaS services and models.

Install

Install with pip.

pip install orchard-lime

Setup

Prepare a configuration file named lime.yaml with the following content. Change MaaS and API KEY if needed.

maas:
  base_url: "https://api.siliconflow.cn/v1"
  api_key: ""
  default_model: ""
  models:
    - "Qwen/Qwen2-7B-Instruct"
    - "Qwen/Qwen2-1.5B-Instruct"
    - "Qwen/Qwen1.5-7B-Chat"
    - "THUDM/glm-4-9b-chat"
    - "THUDM/chatglm3-6b"
    - "01-ai/Yi-1.5-9B-Chat-16K"
    - "01-ai/Yi-1.5-6B-Chat"
    - "google/gemma-2-9b-it"
    - "internlm/internlm2_5-7b-chat"
    - "meta-llama/Meta-Llama-3-8B-Instruct"
    - "meta-llama/Meta-Llama-3.1-8B-Instruct"
    - "mistralai/Mistral-7B-Instruct-v0.2"

Start with uvicorn.

uvicorn lime.main:app --reload --port 10000

Usage

Use HTTP API with curl.

curl -X POST "http://127.0.0.1:10000/v1/chat/completions" -H "Content-Type: application/json" -d '{
  "model": "Qwen/Qwen2-7B-Instruct",
  "messages": [{"role": "user", "content": "Who are you?"}]
}'

Use bascket command.

basket maas use Lime

basket model use Qwen/Qwen2-7B-Instruct

basket chat "what is the meaning of life?"

Project details


Download files

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

Source Distribution

orchard_lime-0.1.0.tar.gz (7.2 kB view details)

Uploaded Source

Built Distribution

orchard_lime-0.1.0-py3-none-any.whl (7.8 kB view details)

Uploaded Python 3

File details

Details for the file orchard_lime-0.1.0.tar.gz.

File metadata

  • Download URL: orchard_lime-0.1.0.tar.gz
  • Upload date:
  • Size: 7.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.11.0 pkginfo/1.9.6 requests/2.28.2 setuptools/65.6.3 requests-toolbelt/0.9.1 tqdm/4.65.0 CPython/3.9.16

File hashes

Hashes for orchard_lime-0.1.0.tar.gz
Algorithm Hash digest
SHA256 64719ef4dae8b61b3844d178bcec31b6a65abb6a58934bc07375a28ffa016199
MD5 85fabdec3700608c20940a2a455b8883
BLAKE2b-256 13295389c8fb900584bed1dbd7499fe8322e2620ffe3a8d486965dc429c307d9

See more details on using hashes here.

File details

Details for the file orchard_lime-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: orchard_lime-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 7.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.11.0 pkginfo/1.9.6 requests/2.28.2 setuptools/65.6.3 requests-toolbelt/0.9.1 tqdm/4.65.0 CPython/3.9.16

File hashes

Hashes for orchard_lime-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fcb2c8f3fa95d432f3c493d91119f30e37f892f1d0a20c70d2c921ff79df0311
MD5 cca243355243879c72c72a84250f3d49
BLAKE2b-256 7be2e821b3fa28b6c9925af6e0c823fdb3dbca64f4a559b73a1b5913866de13a

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page