Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add instruction to set openai configuration information #12531

Merged
merged 4 commits into from
Jun 20, 2023
Merged

Add instruction to set openai configuration information #12531

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7ca3e85
Add instruction to set openai configuration information
d61h6k4 Jun 20, 2023
235129c
Fix review comment
d61h6k4 Jun 20, 2023
051fa06
Add examples of setting Azure parameters for windows
d61h6k4 Jun 20, 2023
326b772
Add API key tab for consistency
d61h6k4 Jun 20, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
62 changes: 55 additions & 7 deletions docs/docs/llms/llm-setup.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,8 +47,18 @@ interaction between the two.

To configure the API token, follow these steps:

1. [Instructions to get your API token]
2. [Instructions to set the token in your LLM configuration]
1. If you haven't already, sign up for an account on the OpenAI platform.

2. Navigate to the [OpenAI Key Management page](https://platform.openai.com/account/api-keys),
and click on the "Create New Secret Key" button to initiate the process of
obtaining your API key.

3. To set the API key as an environment variable, you can use the following command in a
terminal or command prompt:
```shell
m-vdb marked this conversation as resolved.
Show resolved Hide resolved
export OPENAI_API_KEY=<your-api-key>
```
Replace `<your-api-key>` with the actual API key you obtained from the OpenAI platform.

### Model Configuration

Expand All @@ -70,14 +80,52 @@ to be configured:
OpenAI Service.
- `openai.api_base`: This should be the URL for your Azure OpenAI instance. An
example might look like this: "https://docs-test-001.openai.azure.com/".
- `openai.api_version`: This should be the version of Azure OpenAI you are
using, such as "2023-05-15".


To configure these parameters, follow these steps:

1. [Instructions to set `openai.api_type`]
2. [Instructions to set `openai.api_base`]
3. [Instructions to set `openai.api_version`]
1. To configure the `openai.api_type` as an environment variable:
m-vdb marked this conversation as resolved.
Show resolved Hide resolved

<Tabs groupId="os-dist-api-type" values={[{"label": "Linux/MacOS", "value": "unix"}, {"label": "Windows", "value": "windows"}]} defaultValue="unix">
<TabItem value="unix">

```shell
export OPENAI_API_TYPE="azure"
```

</TabItem>
<TabItem value="windows">

```shell
setx OPENAI_API_TYPE "azure"
```

This will apply to future cmd prompt window, so you will need to open a new one to use that variable

</TabItem>
</Tabs>

2. To configure the `openai.api_base` as an environment variable:
m-vdb marked this conversation as resolved.
Show resolved Hide resolved

<Tabs groupId="os-dist-api-base" values={[{"label": "Linux/MacOS", "value": "unix"}, {"label": "Windows", "value": "windows"}]} defaultValue="unix">
<TabItem value="unix">

```shell
export OPENAI_API_BASE=<your-azure-openai-instance-url>
```

</TabItem>
<TabItem value="windows">

```shell
setx OPENAI_API_BASE <your-azure-openai-instance-url>
```

This will apply to future cmd prompt window, so you will need to open a new one to use that variable

</TabItem>
</Tabs>


## Other LLM providers

Expand Down