v3.1.1

[assafelovic]

We've completely refactored almost the entire codebase (over 55 files), to improve overall modularity and simplification of structure to ensure less bugs, and more easy development. In addition, we've finally added image support (!!!). We've also improve the GPT Researcher PIP package which can now return source results, scraped images, research report sections and more! Lastly, thanks to the amazing community you can check out below much more improvements. Thank you to everyone!

Updated Demo with images

gptr-demo-final.mp4

New PIP functions

from gpt_researcher import GPTResearcher
import asyncio

async def get_report(query: str, report_type: str):
researcher = GPTResearcher(query, report_type)
research_result = await researcher.conduct_research()
report = await researcher.write_report()

# Get additional information
research_context = researcher.get_research_context()
research_costs = researcher.get_costs()
research_images = researcher.get_research_images()
research_sources = researcher.get_research_sources()

return report, research_context, research_costs, research_images, research_sources

if name == "main":
query = "what team may win the NBA finals?"
report_type = "research_report"

report, context, costs, images, sources = asyncio.run(get_report(query, report_type))

What's Changed

• Hotfix: Update base.py by @kesamet in Hotfix: Update base.py #902
• Update docstring to reflect default values for temperature and max_tokens in create_chat_completion by @lundha in Update docstring to reflect default values for temperature and max_tokens in create_chat_completion #899
• updated relative paths by @assafelovic in updated relative paths #906
• refactor(Dockerfile): optimize Dockerfile structure and layers by @k1lgor in refactor(Dockerfile): optimize Dockerfile structure and layers #898
• Doc: Typo Fix by @Chhagan011 in Doc: Typo Fix #914
• ✅: Nextjs upgrades by @ElishaKay in ✅: Nextjs upgrades #913
• Feature/improved search queries using prior web search by @assafelovic in Feature/improved search queries using prior web search #919
• [Docs] : Fix typos in docs by @FarukhS52 in [Docs] : Fix typos in docs #920
• fixed some typos in CONTRIBUTING.md by @Smoothengineer in fixed some typos in CONTRIBUTING.md #917
• fixed issue with defaulting to tavily by @assafelovic in fixed issue with defaulting to tavily #924
• Update README.md by @AranavMahalpure in Update README.md #926
• Feature/image support by @assafelovic in Feature/image support #925
• Fixed vector-store.py by @DhanushNehru in Fixed vector-store.py #927
• Update vector-store.py by @DhanushNehru in Update vector-store.py #928
• ✅ showing images in report by @ElishaKay in ✅ showing images in report #930
• update langchain huggingface embedding by @hereiamravi in update langchain huggingface embedding #931

New Contributors

• @lundha made their first contribution in Update docstring to reflect default values for temperature and max_tokens in create_chat_completion #899
• @k1lgor made their first contribution in refactor(Dockerfile): optimize Dockerfile structure and layers #898
• @Chhagan011 made their first contribution in Doc: Typo Fix #914
• @FarukhS52 made their first contribution in [Docs] : Fix typos in docs #920
• @Smoothengineer made their first contribution in fixed some typos in CONTRIBUTING.md #917
• @AranavMahalpure made their first contribution in Update README.md #926
• @DhanushNehru made their first contribution in Fixed vector-store.py #927
• @hereiamravi made their first contribution in update langchain huggingface embedding #931

Full Changelog: v.3.1.0...v3.1.1

---

This discussion was created from the release v3.1.1.