Sweep: create a chat function like completion in upsonic_on_prem/utils/ai/ai.py

[onuratakan]

Checklist

- [X] Modify `upsonic_on_prem/utils/ai/ai.py` ✓ https://github.com/Upsonic/On-Prem/commit/80d2fda59906c473dcf52e06587a74d1b4439172 [Edit](https://github.com/Upsonic/On-Prem/edit/sweep/create_a_chat_function_like_completion_i/upsonic_on_prem/utils/ai/ai.py) - [X] Running GitHub Actions for `upsonic_on_prem/utils/ai/ai.py` ✓ [Edit](https://github.com/Upsonic/On-Prem/edit/sweep/create_a_chat_function_like_completion_i/upsonic_on_prem/utils/ai/ai.py)

[onuratakan]

🚀 Here's the PR! #88

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/Upsonic/On-Prem/blob/32357642dd961fdf0b6cc8d56ee91eff372ce0a2/upsonic_on_prem/utils/ai/ai.py#L1-L397

---

Step 2: ⌨️ Coding

• [X] Modify upsonic_on_prem/utils/ai/ai.py ✓ https://github.com/Upsonic/On-Prem/commit/80d2fda59906c473dcf52e06587a74d1b4439172 Edit

  Modify upsonic_on_prem/utils/ai/ai.py with contents:
  • Add a new method named `chat` in the `AI_` class within the `ai.py` file. This method should closely resemble the structure of the `completion` method but be specifically designed for chat interactions.
  • The `chat` method should accept two parameters: `input_text` (the user's input text for the chat) and `model` (the model to use for generating the chat response, with a default value of "gpt-3.5-turbo").
  • Inside the `chat` method, use the `gpt` method to send the `input_text` to the specified model and return the response. This leverages the existing infrastructure for interacting with AI models and ensures consistency in how models are utilized across the module.
  • Example method signature: `def chat(self, input_text, model="gpt-3.5-turbo"):`
  • Inside the `chat` method, construct the request to the model in a manner that is suitable for chat interactions. This may involve setting up the `input_text` as part of a conversation context if the model supports such a format.
  • Return the response from the model directly or format it as needed before returning to the caller.
  • Ensure that the method includes error handling, similar to other methods in the `AI_` class, to gracefully manage any issues that arise during the interaction with the model.

--- 
+++ 
@@ -395,4 +395,11 @@

         return result

+    def chat(self, input_text, model="gpt-3.5-turbo"):
+        try:
+            return self.gpt(input_text, model=model)
+        except Exception as e:
+            failed(f"Failed to generate chat response: {e}")
+            return None
+
 AI = AI_()

• [X] Running GitHub Actions for upsonic_on_prem/utils/ai/ai.py ✓ Edit

  Check upsonic_on_prem/utils/ai/ai.py with contents:

Ran GitHub Actions for 80d2fda59906c473dcf52e06587a74d1b4439172:

---

Step 3: 🔁 Code Review

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

---

🎉 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.