Sweep (slow): OPENAI_API_BASE is not working

[mckbrchill]

Details

Bugs: OPENAI_API_BASE env variable is not working, because of the bug in openai-async 0.11.0, and it was fixed in 0.12.2.
Features:
Refactors: Refactor code accordingly to latest version of openai-async (or at least 0.12.2). The diff between theese two versions also incorporate function calling capabitily, so it affects completion object type.

Checklist

• Modify Cargo.toml ✓ 9028d9d Edit
• Running GitHub Actions for Cargo.toml ✓ Edit
• Modify src/models.rs ✓ 1f6d9e4 Edit
• Running GitHub Actions for src/models.rs ✓ Edit
• Modify README.md ✓ bdb6ae9 Edit
• Running GitHub Actions for README.md ✓ Edit

[sweep-ai]

🚀 Here's the PR! #112

See Sweep's progress at the progress dashboard!

⚡ Sweep Basic Tier: I'm using GPT-4. You have 5 GPT-4 tickets left for the month and 3 for the day. (tracking ID: 03fcb0c86f)

For more GPT-4 tickets, visit our payment portal. For a one week free trial, try Sweep Pro (unlimited GPT-4 tickets).

---

Tip

I can email you next time I complete a pull request if you set up your email here!

---

Actions (click)

• ↻ Restart Sweep

GitHub Actions✓

Here are the GitHub Actions logs prior to making any changes:

Sandbox logs for 47b6dad

Checking Cargo.toml for syntax errors... ✅ Cargo.toml has no syntax errors! 1/1 ✓

Checking Cargo.toml for syntax errors...
✅ Cargo.toml has no syntax errors!

Sandbox passed on the latest main, so sandbox checks will be enabled for this issue.

---

Step 1: 🔎 Searching

I found the following snippets in your repository. I will now analyze these snippets and come up with a plan.

Some code snippets I think are relevant in decreasing order of relevance (click to expand). If some file is missing from here, you can mention the path in the ticket description.

motorhead/src/models.rs

Lines 57 to 75 in 47b6dad

	}
	_ => {
	let openai_api_base = env::var("OPENAI_API_BASE");
	if let Ok(openai_api_base) = openai_api_base {
	let embedding_config = OpenAIConfig::default().with_api_base(&openai_api_base);
	let completion_config = OpenAIConfig::default().with_api_base(&openai_api_base);
	AnyOpenAIClient::OpenAI {
	embedding_client: Client::with_config(embedding_config),
	completion_client: Client::with_config(completion_config),
	}
	} else {
	AnyOpenAIClient::OpenAI {
	embedding_client: Client::new(),
	completion_client: Client::new(),
	}
	}
	}

motorhead/README.md

Lines 98 to 100 in 47b6dad

	- `PORT` (default:8000) - Motorhead Server Port
	- `OPENAI_API_KEY`- [Your api key](https://platform.openai.com/account/api-keys) to connect to OpenAI.
	- `REDIS_URL` (required)- URL used to connect to `redis`.

---

Step 2: ⌨️ Coding

• Modify Cargo.toml ✓ 9028d9d Edit

Modify Cargo.toml with contents:
• Update the `openai-async` dependency version to `0.12.2` to incorporate the bug fix and new features. This will be done by locating the `openai-async` line in the `Cargo.toml` file and changing the version specified to `0.12.2`. This change is necessary to resolve the bug with the `OPENAI_API_BASE` environment variable and to make use of the updated function calling capability in the newer version.

--- 
+++ 
@@ -9,7 +9,7 @@
 
 [dependencies]
 actix-web = "4.3"
-async-openai = "0.11.0"
+async-openai = "0.12.2"
 async-trait = "0.1.68"
 byteorder = "1.4.3"
 chrono = "0.4.24"

• Running GitHub Actions for Cargo.toml ✓ Edit

Check Cargo.toml with contents:

Ran GitHub Actions for 9028d9d5e567e9f221a7825c10c0f9a0c321e033:

• Modify src/models.rs ✓ 1f6d9e4 Edit

Modify src/models.rs with contents:
• Refactor the instantiation of `OpenAIConfig` objects and their usage with the `Client` to be compatible with changes introduced in `openai-async` version 0.12.2. This includes adjusting how the `OPENAI_API_BASE` is applied to the `OpenAIConfig` and ensuring that the completion object type is correctly handled according to the new version's requirements. Specific changes may involve updating method names, parameters, or how configurations are applied, based on the differences between `openai-async` versions 0.11.0 and 0.12.2.
• Ensure that any new functionality or changes in how the `Client` is configured or used are correctly implemented to maintain or enhance the existing functionality.

--- 
+++ 
@@ -59,12 +59,12 @@
                 let openai_api_base = env::var("OPENAI_API_BASE");
 
                 if let Ok(openai_api_base) = openai_api_base {
-                    let embedding_config = OpenAIConfig::default().with_api_base(&openai_api_base);
-                    let completion_config = OpenAIConfig::default().with_api_base(&openai_api_base);
+                    let embedding_config = OpenAIConfig::new().api_base(&openai_api_base);
+                    let completion_config = OpenAIConfig::new().api_base(&openai_api_base);
 
                     AnyOpenAIClient::OpenAI {
-                        embedding_client: Client::with_config(embedding_config),
-                        completion_client: Client::with_config(completion_config),
+                        embedding_client: Client::new(&embedding_config),
+                        completion_client: Client::new(&completion_config),
                     }
                 } else {
                     AnyOpenAIClient::OpenAI {

• Running GitHub Actions for src/models.rs ✓ Edit

Check src/models.rs with contents:

Ran GitHub Actions for 1f6d9e4592be05d75d05891cf12c632ba2301c9b:

• Modify README.md ✓ bdb6ae9 Edit

Modify README.md with contents:
• Add documentation for the `OPENAI_API_BASE` environment variable. This should include a brief description of what the variable is used for, how to set it, and a default value if applicable. This update ensures that users are aware of how to configure the `OPENAI_API_BASE` to point to the correct OpenAI API base URL, which is crucial for the correct operation of the application in environments where the default API base URL may need to be overridden.

--- 
+++ 
@@ -98,7 +98,7 @@
 - `PORT` (default:8000) - Motorhead Server Port
 - `OPENAI_API_KEY`- [Your api key](https://platform.openai.com/account/api-keys) to connect to OpenAI.
 - `REDIS_URL` (required)- URL used to connect to `redis`.
-- `OPENAI_API_BASE` (default:https://api.openai.com/v1) - OpenAI API Base URL
+- `OPENAI_API_BASE` (default:https://api.openai.com/v1) - This environment variable specifies the base URL for the OpenAI API. It's used by the Motorhead server to make API calls to OpenAI for its operations. In most cases, the default value should suffice. However, if you're working with a different OpenAI API endpoint or in an environment where the standard OpenAI endpoints are overridden, you'll need to set this variable accordingly. To set it, use `OPENAI_API_BASE='your_custom_api_base_url'` in your environment configuration.
 
 ### Azure deployment
 

• Running GitHub Actions for README.md ✓ Edit

Check README.md with contents:

Ran GitHub Actions for bdb6ae98a88ea1d0cee9ddd9d01d15c1b86eb29f:

---

Step 3: 🔁 Code Review

I have finished reviewing the code for completeness. I did not find errors for sweep/openai_api_base_is_not_working.

---

🎉 Latest improvements to Sweep:

• New dashboard launched for real-time tracking of Sweep issues, covering all stages from search to coding.
• Integration of OpenAI's latest Assistant API for more efficient and reliable code planning and editing, improving speed by 3x.
• Use the GitHub issues extension for creating Sweep issues directly from your editor.

💡 To recreate the pull request edit the issue title or description. To tweak the pull request, leave a comment on the pull request.^{Something wrong? Let us know.}

This is an automated message generated by Sweep AI.