Ready, Set, Launch! 🚀

Prompts

✅ Easy to Create Prompts in Playground

✅ Prompt Management

✅ Versioning Support

✅ OpenAI Function Support

✅ Run all Scenarios at once

🕒 AI Co-Pilot to craft better prompts

🕒 Support for Llama-2, Anthropic

🕒 Test Cases & Quantitative Evaluation

🕒 Auto-Generated Annotations in History Tracking

Observability

✅ Realtime logs

✅ 3 Custom Metadata & Filters

🕒 Observability over Chain

🕒 Visualize & Share your runs

🕒 Add a run to testing dataset

Monitoring

✅ Monitor Spending w.r.t 15+ filters

✅ Application level usage statistics

✅ Feedback Collection

✅ Error Analytics

✅ User Analytics

✅ 15+ filters

✅ Analyze Traffic peaks

✅ Track Latency patterns

Testing & Eval (Coming Soon)

🕒 Dataset Curation

🕒 Evaluate Chain Performance

🕒 AI-Assisted Evaluation

🕒 Easy Benchmarking

Middleware Tools (Coming Soon)

🕒 Caching

🕒 A/B Testing

🕒 Fallbacks

🕒 Retries

🕒 Key Provider Vault

🕒 PII Remover

🕒 Omit Logs