sweep-nightly[bot]
commented
7 months ago 🚀 Here's the PR! #3265
See Sweep's progress at the progress dashboard!
💎 Sweep Pro: I'm using GPT-4. You have unlimited GPT-4 tickets. (tracking ID:
None)[!TIP] I can email you next time I complete a pull request if you set up your email here!
Actions (click)
- [ ] ↻ Restart Sweep
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.
https://github.com/sweepai/sweep/blob/47caf9787d47e95299be7e85704499eb167bd3c1/docs/pages/usage/extra-self-host.mdx#L35-L65Step 2: ⌨️ Coding
- [X] Modify
docs/pages/usage/extra-self-host.mdx✓ https://github.com/sweepai/sweep/commit/fd0640ea99307189481685bfc242f603887bc808 EditModify docs/pages/usage/extra-self-host.mdx with contents:
• Remove the section starting from the header "### 4. Test other LLMs" down to the code block that sets the OPENAI_API_BASE and OPENAI_API_KEY environment variables. This includes the header, the LiteLLM installation and setup instructions, and the environment variable setup instructions.
• Specifically, delete lines 35 through 65 from the extra-self-host.mdx file.
• Ensure that the removal of this section does not affect the formatting or flow of the surrounding content. If necessary, adjust the surrounding text to maintain a coherent structure in the document.
--- +++ @@ -33,34 +33,6 @@ ``` OPENAI_DO_HAVE_32K_MODEL_ACCESS=true ``` -### 4. Test other LLMs -#### Huggingface, Palm, Ollama, TogetherAI, AI21, Cohere etc.[Full List](https://docs.litellm.ai/docs/providers) -##### Create OpenAI-proxy -We'll use [LiteLLM](https://docs.litellm.ai/docs/) to create an OpenAI-compatible endpoint, that translates OpenAI calls to any of the [supported providers](https://docs.litellm.ai/docs/providers). -Example to use a local CodeLLama model from Ollama.ai with Sweep: - -Let's spin up a proxy server to route any OpenAI call from Sweep to Ollama/CodeLlama -```python -pip install litellm -``` -```python -$ litellm --model ollama/codellama - -#INFO: Ollama running on http://0.0.0.0:8000 -``` - -[Docs](https://docs.litellm.ai/docs/proxy_server) - -### Update Sweep - -Update your .env - -```shell -os.environ["OPENAI_API_BASE"] = "http://0.0.0.0:8000" -os.environ["OPENAI_API_KEY"] = "my-fake-key" -``` - -Note: All of Sweep's testing has been done on GPT-4. We've tested and on most of our prompts, even GPT-3.5 and Claude v2 breaks most of the time.
- [X] Running GitHub Actions for
docs/pages/usage/extra-self-host.mdx✓ EditCheck docs/pages/usage/extra-self-host.mdx with contents:
Ran GitHub Actions for fd0640ea99307189481685bfc242f603887bc808:
Step 3: 🔁 Code Review
I have finished reviewing the code for completeness. I did not find errors for sweep/remove_the_litellm_section_in_httpsdocss.
🎉 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. Something wrong? Let us know.
This is an automated message generated by Sweep AI.
Branch
No response
Checklist
- [X] Modify `docs/pages/usage/extra-self-host.mdx` ✓ https://github.com/sweepai/sweep/commit/fd0640ea99307189481685bfc242f603887bc808 [Edit](https://github.com/sweepai/sweep/edit/sweep/remove_the_litellm_section_in_httpsdocss/docs/pages/usage/extra-self-host.mdx) - [X] Running GitHub Actions for `docs/pages/usage/extra-self-host.mdx` ✓ [Edit](https://github.com/sweepai/sweep/edit/sweep/remove_the_litellm_section_in_httpsdocss/docs/pages/usage/extra-self-host.mdx)