Starstruk Logo MarkStarstruk

v0.1.1

assafelovic/gpt-researcherv0.1.1Nov 25, 2023by assafelovic

AI Summary

Focuses on performance optimization using Contextual Compression and embeddings, significantly reducing research time and GPT token costs.

Key Highlights

  • Contextual Compression approach for information retrieval
  • 60% reduction in research task time
  • 30% increase in research quality
  • 50% reduction in GPT costs

New Features

  • Contextual Compression
  • Embedding-based retrieval

Full Release Notes

Excited to release the latest version aimed at improving overall research performance! 🎉

We're introducing a new approach to extracting relevant information from scraped sites using Contextual Compression. We now leverage embeddings to better store and retrieve information across the research lifecycle. This latest improvement reduces research task time by an average of 60%, increases quality by ~30% and reduces GPT costs by 50% (we don't summarize with GPT anymore).

In addition, thank you to our amazing contributors:
@reasonmethis for the serp retriever fix: https://github.com/assafelovic/gpt-researcher/pull/261
@devon-ye for the Chinese README addition: https://github.com/assafelovic/gpt-researcher/pull/254