feat(blocks): Add AI/ML API support to LLM blocks

[waterstark]

Changes 🏗️

• Added basic functionality to enable users to send requests to our models.
• Added instructions for users on how to use the AI/ML API in AutoGPT.

Checklist 📋

For code changes:

• I have clearly listed my changes in the PR description
• I have made a test plan
• I have tested my changes according to the test plan:
  • The API key has been successfully added and saved to the user's profile.
  • Sending requests to each model provided by us, enabling users to test them in a project with various max_tokens parameter values and other configurations.

Example test plan

• Create from scratch and execute an agent with at least 3 blocks
• Import an agent from file upload, and confirm it executes correctly
• Upload agent to marketplace
• Import an agent from marketplace and confirm it executes correctly
• Edit an agent from monitor, and confirm it executes correctly

For configuration changes:

• .env.example is updated or already compatible with my changes
• docker-compose.yml is updated or already compatible with my changes
• I have included a list of my configuration changes in the PR description (under Changes)

Examples of configuration changes

• Changing ports
• Adding new services that need to communicate with each other
• Secrets or environment variable changes
• New or infrastructure changes such as databases

[CLAassistant]

All committers have signed the CLA.

[github-actions]

This PR targets the master branch but does not come from dev or a hotfix/* branch.

Automatically setting the base branch to dev.

[qodo-merge-pro]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 4 🔵🔵🔵🔵⚪

🧪 No relevant tests

🔒 Security concerns API Key Exposure: The AIML API key is stored in environment variables and configuration files. While this is a common practice, ensure the .env file and configuration files have proper access restrictions and are not accidentally committed to version control.

⚡ Recommended focus areas for review Error Handling The AIML provider implementation lacks proper error handling for API failures and rate limits. Should add try-catch blocks and handle common API errors. elif provider == "aiml": client = openai.OpenAI( base_url="https://api.aimlapi.com/v2", api_key=credentials.api_key.get_secret_value(), ) completion = client.chat.completions.create( model=llm_model.value, messages=prompt, # type: ignore max_tokens=max_tokens, ) # response = completion.choices[0].message.content return ( completion.choices[0].message.content or "", completion.usage.prompt_tokens if completion.usage else 0, completion.usage.completion_tokens if completion.usage else 0, ) else: Token Counting Using GPT-3.5-turbo tokenizer as a hack for AIML models may lead to incorrect token counting since different models can have different tokenization schemes. def get_tokenizer(self, model_name: AimlModelName) -> ModelTokenizer[Any]: # HACK: No official tokenizer is available for AIML return tiktoken.encoding_for_model("gpt-3.5-turbo") Model Validation The code should validate that the provided model name exists in the AIML provider's model list before making API calls. completion = client.chat.completions.create( model=llm_model.value, messages=prompt, # type: ignore max_tokens=max_tokens, )

[netlify]

✅ Deploy Preview for auto-gpt-docs canceled.

Name	Link
🔨 Latest commit	32b7b56
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs/deploys/67a482df31dd600008f2e0c4

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Please upload report for BASE (dev@1ce1918). Learn more about missing BASE report.

Additional details and impacted files

@@          Coverage Diff           @@
##             dev    #9163   +/-   ##
======================================
  Coverage       ?   33.94%           
======================================
  Files          ?       16           
  Lines          ?     1258           
  Branches       ?      190           
======================================
  Hits           ?      427           
  Misses         ?      804           
  Partials       ?       27           

Flag	Coverage Δ
Linux	33.94% <ø> (?)
Windows	33.94% <ø> (?)
autogpt-agent	33.94% <ø> (?)
macOS	33.94% <ø> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[netlify]

✅ Deploy Preview for auto-gpt-docs-dev canceled.

Name	Link
🔨 Latest commit	32b7b56
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs-dev/deploys/67a482dfd3c2f7000877d025

[deepsource-io]

Here's the code health analysis summary for commits 6183ed5..32b7b56. View details on DeepSource ↗.

Analysis Summary

Analyzer	Status	Summary	Link
JavaScript	✅ Success		View Check ↗
Python	✅ Success	❗ 2 occurences introduced 🎯 2 occurences resolved	View Check ↗

---

💡 If you’re a repository administrator, you can configure the quality gates from the settings.

[github-actions]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[github-actions]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[aarushik93]

@waterstark do you mind please fixing the test!

[waterstark]

Yes, yes, sorry I didn’t have enough time to roll out the fix yesterday.

[waterstark]

@aarushik93 Could you please check the error in page.tsx? I didn’t make any changes to this file, and I don’t know JavaScript. If you can help, I would really appreciate it.