docs: add AI provider examples for all LLM analytics integrations#478
Merged
richardsolomou merged 4 commits intomasterfrom Apr 7, 2026
Merged
docs: add AI provider examples for all LLM analytics integrations#478richardsolomou merged 4 commits intomasterfrom
richardsolomou merged 4 commits intomasterfrom
Conversation
Add 26 new example directories covering every provider documented in our LLM analytics onboarding docs. This includes OpenAI-compatible providers (Groq, DeepSeek, Mistral, xAI, Together AI, Ollama, Cohere, Hugging Face, Perplexity, Cerebras, Fireworks AI, OpenRouter, Helicone, Vercel AI Gateway, Azure OpenAI, Portkey) and custom integrations (Instructor, LangGraph, AWS Bedrock, CrewAI, Mirascope, LlamaIndex, DSPy, Semantic Kernel, smolagents, AutoGen).
Contributor
posthog-python Compliance ReportDate: 2026-04-07 08:05:38 UTC ✅ All Tests Passed!0/0 tests passed |
Mistral's API doesn't support max_completion_tokens, causing 422 errors.
|
Review the following changes in direct dependencies. Learn more about Socket for GitHub.
|
Mirascope doesn't pass extra kwargs through to the OpenAI client. Tracking still works via the wrapped client.
Radu-Raicea
approved these changes
Apr 3, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
We have documentation for 38 LLM analytics integrations but only had 7 working examples in the repo. Users and the example runner in llm-analytics-apps couldn't test most integrations.
Changes
Add 26 new example directories covering every provider documented in our LLM analytics onboarding docs:
OpenAI-compatible providers (16): Groq, DeepSeek, Mistral, xAI, Together AI, Ollama, Cohere, Hugging Face, Perplexity, Cerebras, Fireworks AI, OpenRouter, Helicone, Vercel AI Gateway, Azure OpenAI, Portkey
Custom integrations (10): Instructor, LangGraph, AWS Bedrock, CrewAI, Mirascope, LlamaIndex, DSPy, Semantic Kernel, smolagents, AutoGen
Each example follows the same structure as existing examples (pyproject.toml, uv.toml, .env.example, README.md, and the main .py file).
How did you test this code?
Verified all examples are discovered by the llm-analytics-apps example runner (
./run-examples.sh --listshows 91 examples).