Skip to content

Commit

Permalink
cleanup
Browse files Browse the repository at this point in the history
  • Loading branch information
sonichi committed Sep 27, 2023
1 parent eef911d commit ddf1004
Show file tree
Hide file tree
Showing 6 changed files with 90 additions and 7 deletions.
2 changes: 1 addition & 1 deletion autogen/oai/openai_utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,7 @@ def config_list_openai_aoai(
# Assuming Azure OpenAI api bases in os.environ["AZURE_OPENAI_API_BASE"], in separated lines
api_bases=os.environ.get("AZURE_OPENAI_API_BASE", "").split("\n"),
api_type="azure",
api_version="2023-06-01-preview", # change if necessary
api_version="2023-07-01-preview", # change if necessary
)
if exclude != "aoai"
else []
Expand Down
2 changes: 1 addition & 1 deletion notebook/agentchat_function_call.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@
"It's OK to have only the OpenAI API key, or only the Azure OpenAI API key + base.\n",
"If you open this notebook in google colab, you can upload your files by click the file icon on the left panel and then choose \"upload file\" icon.\n",
"\n",
"The following code excludes Azure OpenAI endpoints from the config list because they don't support functions yet. Remove the `exclude` argument after they do."
"The following code excludes Azure OpenAI endpoints from the config list because some endpoints don't support functions yet. Remove the `exclude` argument if they do."
]
},
{
Expand Down
4 changes: 2 additions & 2 deletions notebook/agentchat_planning.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -97,14 +97,14 @@
" 'api_key': '<your Azure OpenAI API key here>',\n",
" 'api_base': '<your Azure OpenAI API base here>',\n",
" 'api_type': 'azure',\n",
" 'api_version': '2023-06-01-preview',\n",
" 'api_version': '2023-07-01-preview',\n",
" }, # Azure OpenAI API endpoint for gpt-4\n",
" {\n",
" 'model': 'gpt-4-32k',\n",
" 'api_key': '<your Azure OpenAI API key here>',\n",
" 'api_base': '<your Azure OpenAI API base here>',\n",
" 'api_type': 'azure',\n",
" 'api_version': '2023-06-01-preview',\n",
" 'api_version': '2023-07-01-preview',\n",
" }, # Azure OpenAI API endpoint for gpt-4-32k\n",
"]\n",
"```\n",
Expand Down
4 changes: 2 additions & 2 deletions notebook/agentchat_two_users.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -70,14 +70,14 @@
" \"api_key\": \"<your Azure OpenAI API key here>\",\n",
" \"api_base\": \"<your Azure OpenAI API base here>\",\n",
" \"api_type\": \"azure\",\n",
" \"api_version\": \"2023-06-01-preview\"\n",
" \"api_version\": \"2023-07-01-preview\"\n",
" },\n",
" {\n",
" \"model\": \"gpt-4-32k\",\n",
" \"api_key\": \"<your Azure OpenAI API key here>\",\n",
" \"api_base\": \"<your Azure OpenAI API base here>\",\n",
" \"api_type\": \"azure\",\n",
" \"api_version\": \"2023-06-01-preview\"\n",
" \"api_version\": \"2023-07-01-preview\"\n",
" }\n",
"]\n",
"```\n",
Expand Down
83 changes: 83 additions & 0 deletions website/docs/FAQ.md
Original file line number Diff line number Diff line change
@@ -1 +1,84 @@
# Frequently Asked Questions

## Set your API endpoints

There are multiple ways to construct a list of configurations for LLM inference.

### Load a list of endpoints from json

The [`config_list_from_json`](/docs/reference/autogen/oai/openai_utils#config_list_from_json) function loads a list of configurations from an environment variable or a json file.

For example,

```python
import autogen
config_list = autogen.config_list_from_json(
"OAI_CONFIG_LIST",
file_location=".",
filter_dict={
"model": {
"gpt-4",
"gpt-3.5-turbo",
}
}
)
```

It first looks for environment variable "OAI_CONFIG_LIST" which needs to be a valid json string. If that variable is not found, it then looks for a json file named "OAI_CONFIG_LIST" under the specified `file_location`. It then filters the configs by models (you can filter by other keys as well).

The `OAI_CONFIG_LIST` var or file content looks like the following:
```json
[
{
"model": "gpt-4",
"api_key": "<your OpenAI API key here>"
},
{
"model": "gpt-4",
"api_key": "<your Azure OpenAI API key here>",
"api_base": "<your Azure OpenAI API base here>",
"api_type": "azure",
"api_version": "2023-07-01-preview"
},
{
"model": "gpt-3.5-turbo",
"api_key": "<your Azure OpenAI API key here>",
"api_base": "<your Azure OpenAI API base here>",
"api_type": "azure",
"api_version": "2023-07-01-preview"
},
]
```

### Construct a list of endpoints for OpenAI or Azure OpenAI

he [`config_list_from_models`](/docs/reference/autogen/oai/openai_utils#config_list_from_models) function tries to create a list of configurations using Azure OpenAI endpoints and OpenAI endpoints for the provided list of models. It assumes the api keys and api bases are stored in the corresponding environment variables or local txt files:

- OpenAI API key: os.environ["OPENAI_API_KEY"] or `openai_api_key_file="key_openai.txt"`.
- Azure OpenAI API key: os.environ["AZURE_OPENAI_API_KEY"] or `aoai_api_key_file="key_aoai.txt"`. Multiple keys can be stored, one per line.
- Azure OpenAI API base: os.environ["AZURE_OPENAI_API_BASE"] or `aoai_api_base_file="base_aoai.txt"`. Multiple bases can be stored, one per line.

It's OK to have only the OpenAI API key, or only the Azure OpenAI API key + base.

```python
import autogen
config_list = autogen.config_list_from_models(model_list=["gpt-4", "gpt-3.5-turbo", "gpt-3.5-turbo-16k"])
```

The config list looks like the following, if only OpenAI API key is available:
```python
config_list = [
{
'model': 'gpt-4',
'api_key': '<your OpenAI API key here>',
}, # OpenAI API endpoint for gpt-4
{
'model': 'gpt-3.5-turbo',
'api_key': '<your OpenAI API key here>',
}, # OpenAI API endpoint for gpt-3.5-turbo
{
'model': 'gpt-3.5-turbo-16k',
'api_key': '<your OpenAI API key here>',
}, # OpenAI API endpoint for gpt-3.5-turbo-16k
]
```
2 changes: 1 addition & 1 deletion website/docs/Use-Cases/enhanced_inference.md
Original file line number Diff line number Diff line change
Expand Up @@ -135,7 +135,7 @@ response = autogen.Completion.create(
"api_key": os.environ.get("AZURE_OPENAI_API_KEY"),
"api_type": "azure",
"api_base": os.environ.get("AZURE_OPENAI_API_BASE"),
"api_version": "2023-06-01-preview",
"api_version": "2023-07-01-preview",
},
{
"model": "gpt-3.5-turbo",
Expand Down

0 comments on commit ddf1004

Please sign in to comment.