kenken999's picture
fda
0f43f8a
raw
history blame
1.93 kB
---
title: Cloudflare Workers AI
---
To use Open Interpreter with the Cloudflare Workers AI API, set the `model` flag:
<CodeGroup>
```bash Terminal
interpreter --model cloudflare/<cloudflare-model>
```
```python Python
from interpreter import interpreter
interpreter.llm.model = "cloudflare/<cloudflare-model>"
interpreter.chat()
```
</CodeGroup>
# Supported Models
We support the following completion models from Cloudflare Workers AI:
- Llama-2 7b chat fp16
- Llama-2 7b chat int8
- Mistral 7b instruct v0.1
- CodeLlama 7b instruct awq
<CodeGroup>
```bash Terminal
interpreter --model cloudflare/@cf/meta/llama-2-7b-chat-fp16
interpreter --model cloudflare/@cf/meta/llama-2-7b-chat-int8
interpreter --model @cf/mistral/mistral-7b-instruct-v0.1
interpreter --model @hf/thebloke/codellama-7b-instruct-awq
```
```python Python
interpreter.llm.model = "cloudflare/@cf/meta/llama-2-7b-chat-fp16"
interpreter.llm.model = "cloudflare/@cf/meta/llama-2-7b-chat-int8"
interpreter.llm.model = "@cf/mistral/mistral-7b-instruct-v0.1"
interpreter.llm.model = "@hf/thebloke/codellama-7b-instruct-awq"
```
</CodeGroup>
# Required Environment Variables
Set the following environment variables [(click here to learn how)](https://chat.openai.com/share/1062cdd8-62a1-4aa8-8ec9-eca45645971a) to use these models.
| Environment Variable | Description | Where to Find |
| ----------------------- | -------------------------- | ---------------------------------------------------------------------------------------------- |
| `CLOUDFLARE_API_KEY'` | Cloudflare API key | [Cloudflare Profile Page -> API Tokens](https://dash.cloudflare.com/profile/api-tokens) |
| `CLOUDFLARE_ACCOUNT_ID` | Your Cloudflare account ID | [Cloudflare Dashboard -> Overview page -> API section](https://www.perplexity.ai/settings/api) |