Releases: assafelovic/gpt-researcher
v3.1.4
What's Changed
- nextjs upgrades & security patch by @ElishaKay in #978
- Azure embedding quota limit by @roninio in #979
- fix: passing source_urls limits sources by @ElishaKay in #982
New Contributors
Full Changelog: v3.1.3...v3.1.4
Contributors
Assets 2
New UX + Performance improvements
Excited to introduce a complete revamp to our React application which now provides a much smoother and optimal research experience than before. In addition we have some awesome new features like chatting with your reports, improved pubmed retrieval, additional embedding providers and more! As always, this is many thanks to our incredible community. Keep it coming!
gptr-demo-compressed.mp4
What's Changed
- NextJS Upgrades by @ElishaKay in #951
- Updated Contributing.md by @HimangshuYadav in #952
- Documentation update to correct LLM provider prefix for Azure OpenAI. by @scchengaiah in #958
- Updates code of conduct and removes all the grammatical errors. by @HimangshuYadav in #956
- Updates Readme.md (English version) by @HimangshuYadav in #955
- Sort pubmed_central search results by relevance versus default newest by @cannin in #953
- Add function get_similar_content_by_query_with_vectorstore. by @dzerkes in #961
- Searx retriever refactoring by @igochkov in #960
- Update gptr-logs-handler.py by @DhruvKadam-git in #962
- Chat with History by @khoangothe in #885
- nextjs chat fix by @ElishaKay in #972
- Add embedding providers by @kesamet in #965
- update
getHostreference by @emmanuel-ferdman in #973 - Improved NextJS UX by @assafelovic in #968
New Contributors
- @HimangshuYadav made their first contribution in #952
- @scchengaiah made their first contribution in #958
- @cannin made their first contribution in #953
- @dzerkes made their first contribution in #961
- @igochkov made their first contribution in #960
- @DhruvKadam-git made their first contribution in #962
- @emmanuel-ferdman made their first contribution in #973
Full Changelog: v3.1.2...v3.1.3
Performance and bug fixes
Following the previous release, this release adds various bug fixes and performance improvements to the latest GPTR features including image support, documentation, new improved LLM and embedding configuration (shout out to @kesamet!). This release is recommended to all developers.
What's Changed
- Sanitize filenames file upload/delete by @ethansilvas in #935
- "hack" to fix AzureOpenAI configuration problem by @danieldekay in #933
- Added a "Back To Top" Button by @Akhsuna07 in #937
- Specify embedding provider and model by @kesamet in #918
- added all changes by @assafelovic in #942
- Feature/strategic llm by @assafelovic in #941
- Docs upgrades by @ElishaKay in #940
- Fix/bing retriever consistency by @ibuder in #944
- fix/bing-retriever: add missing import statement by @rylincoln in #948
New Contributors
- @ethansilvas made their first contribution in #935
- @Akhsuna07 made their first contribution in #937
- @ibuder made their first contribution in #944
- @rylincoln made their first contribution in #948
Full Changelog: v3.1.1...v3.1.2
🖼️ Image support and mega refactor
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 #902
- Update docstring to reflect default values for
temperatureandmax_tokensincreate_chat_completionby @lundha in #899 - updated relative paths by @assafelovic in #906
- refactor(Dockerfile): optimize Dockerfile structure and layers by @k1lgor in #898
- Doc: Typo Fix by @Chhagan011 in #914
- ✅: Nextjs upgrades by @ElishaKay in #913
- Feature/improved search queries using prior web search by @assafelovic in #919
- [Docs] : Fix typos in docs by @FarukhS52 in #920
- fixed some typos in CONTRIBUTING.md by @Smoothengineer in #917
- fixed issue with defaulting to tavily by @assafelovic in #924
- Update README.md by @AranavMahalpure in #926
- Feature/image support by @assafelovic in #925
- Fixed vector-store.py by @DhanushNehru in #927
- Update vector-store.py by @DhanushNehru in #928
- ✅ showing images in report by @ElishaKay in #930
- update langchain huggingface embedding by @hereiamravi in #931
New Contributors
- @lundha made their first contribution in #899
- @k1lgor made their first contribution in #898
- @Chhagan011 made their first contribution in #914
- @FarukhS52 made their first contribution in #920
- @Smoothengineer made their first contribution in #917
- @AranavMahalpure made their first contribution in #926
- @DhanushNehru made their first contribution in #927
- @hereiamravi made their first contribution in #931
Full Changelog: v.3.1.0...v3.1.1
v.3.1.0
We've been head down refining each step of the research process to improve code structure, performance, customizability and overall experience. This release is another step toward the best autonomous research agent. For example, you can now choose multiple LLM provider and models per research task as seen here: https://docs.gptr.dev/docs/gpt-researcher/gptr/config
Thank you as always to the best community!
What's Changed
- Simple Docker files optimization. by @yigit353 in #843
- Removed favicon.ico to resolve duplication error by @yigit353 in #848
- Update linux-deployment.md by @yigit353 in #849
- Add SearchApi retriever by @SebastjanPrachovskij in #851
- Update filtering-by-domain.md by @danieldekay in #853
- Ollama fixes by @dharmapurikar in #856
- Fixing the missing "os" import for base.py by @dharmapurikar in #857
- Partial fix to chat with Documents by @yigit353 in #863
- Users can upload larger files by @yigit353 in #864
- utils.py: resolve SyntaxWarning by @samyk in #866
- actions: refactor actions for modularity and readability by @Arieg419 in #867
- server: refactor server for modularity and readability by @Arieg419 in #868
- multi-agents, master agent refactor by @Arieg419 in #869
- multi-agents, editor agent refactor by @Arieg419 in #870
- Agent/refactor agent for extendability by @Arieg419 in #871
- revert experiment by @Arieg419 in #872
- config - easy to add custom config by @Arieg419 in #873
- detailed report, fix report creation by @Arieg419 in #875
- Updated Hugging Face embeddings to use all-MiniLM-L6-v2 by @KoradaCharan in #881
- Add Document To Vector Store by @khoangothe in #838
- Make the README translations more consistent by @kevin1kevin1k in #887
- Separate fast and smart llm providers by @kesamet in #813
- Bug fixes/detailed report by @assafelovic in #895
New Contributors
- @yigit353 made their first contribution in #843
- @SebastjanPrachovskij made their first contribution in #851
- @dharmapurikar made their first contribution in #856
- @samyk made their first contribution in #866
- @Arieg419 made their first contribution in #867
- @KoradaCharan made their first contribution in #881
- @kevin1kevin1k made their first contribution in #887
- @kesamet made their first contribution in #813
Full Changelog: v3.0.8...v.3.1.0
Improved quality and scraping support
This week we have some more exciting improvements across the entire GPTR stack. We've improved overall research quality, data source filtering and UX/UI. We've added much more documentation for you to get onboarded and customize GPTR for your needs. Finally, we've added a new scraping option that leverages real browser scraping for improved content extraction and reduced bot detection by various sites. Thank you again to the amazing community!
What's Changed
- Fix Last Paragraph is not Sent to Websocket by @khoangothe in #831
- Update server.py by @danieldekay in #837
- added an example on a custom configuration e.g. Azure by @danieldekay in #836
- Adding Custom Configuration Setup Instructions to GPTR by @monolok in #828
- ✅ ready for review: added, structured & cleaned docs by @ElishaKay in #814
- ✅: Docs fixes by @ElishaKay in #840
- Fix SyntaxError in prompts.py due to conflicting quotes in f-string by @onlydole in #841
- Add browser scraping support by @assafelovic in #842
- Optimize FileUpload Component by @muhammedsaidckr in #824
New Contributors
- @khoangothe made their first contribution in #831
- @monolok made their first contribution in #828
- @onlydole made their first contribution in #841
Full Changelog: v3.0.7...v3.0.8
v3.0.7
This week includes important performance updates and bug fixes making GPT more stable across vendors and use cases. It is highly recommended updating to this latest version! Thanks again to the #1 community on Github!
What's Changed
- Fix package name from logurun to loguru in requirements.txt. Fixes #809 by @ledurnan in #811
- BugFix: Version 0.9.1 cannot be installed #806 by @prasannaJosium in #808
- Bug fixes and improvements by @assafelovic in #823
- [Document] Add korean translation by @RektPunk in #825
- Feature/improved detailed report by @assafelovic in #829
- Update unstructured requirement from ^0.13.0 to >=0.13,<0.16 by @dependabot in #775
- Update langgraph requirement from >=0.0.29,<0.1 to >=0.0.29,<0.3 by @dependabot in #776
New Contributors
- @ledurnan made their first contribution in #811
- @prasannaJosium made their first contribution in #808
- @RektPunk made their first contribution in #825
Full Changelog: v3.0.6...v3.0.7
New NextJS front end application and more!
We're excited to officially launch the new and production ready front end application to GPT Researcher leveraging NextJS and Tailwind CSS! This is another important milestone towards the ultimate automated research assistant and big shoutout to @ElishaKay for leading this all the way. In addition, we have some powerful additions by the best community on GIthub including improvements to vector stores, embedding models, usage of env vars with multi agent framework, bug fixes and more! Check the detailed list below.
What's Changed
- [Fix] No module named 'json5' by @gkhngyk in #770
- ✅ CI / CD - run tests on every commit by @ElishaKay in #690
- Update README.md by @mirkancal in #778
- Fix TypeError in custom reports due to missing 'tone' parameter by @Gitzoz in #784
- Improved azure openai config by @danieldekay in #786
- fix: added missing langgraph to requirements.txt by @danieldekay in #785
- ✅ ready for merge: Fullstack fixes by @ElishaKay in #783
- Enhancement: OpenAI Embedding Model Selection by @eitag-uni in #789
- Update prompts.py by @Einengutenmorgen in #797
- multi-agent approach should now use .env file for config of llm by @danieldekay in #795
- Support langchain vectorstores by @hslee16 in #781
- ✅ ready for merge: nextjs to root by @ElishaKay in #800
- multi_agents/requirements.txt was missing loguru by @sdisaacson in #802
New Contributors
- @mirkancal made their first contribution in #778
- @Gitzoz made their first contribution in #784
- @eitag-uni made their first contribution in #789
- @Einengutenmorgen made their first contribution in #797
- @sdisaacson made their first contribution in #802
Full Changelog: v.3.0.5...v3.0.6
Performance Boost
This week includes a critical update to all GPTR users - we've focused on optimizations and happy to update that GPTR pip package is now 87% lighter (!!). This is big news to all Docker users and has been a long time request. In addition, we've added support for human in the loop to the multi agent solution. This itself marks a new milestone toward better human-agent experience throughout the research processes. Thank you again to the #1 AI community!
What's Changed
- Stabilize master by @ElishaKay in #755
- Optimized project dependencies by @assafelovic in #756
- minimalistic-deps by @ElishaKay in #757
- made use of azure_openai consistent (and not just in the base model, … by @danieldekay in #759
- WIP: Human in the loop - frontend support by @ElishaKay in #762
New Contributors
- @danieldekay made their first contribution in #759
Full Changelog: v3.0.4...v.3.0.5
Hybrid Research support
I get excited with every release but for a reason! We're now releasing support for hybrid research and multiple retrievers! 🤯
You can now conduct research using both local documents and web search for optimal research results! In addition, you can add multiple web retrievers for even better breadth of online information with any of our supported web retrievers. We've tested this on several research queries and found and increase of 38% in research report quality and correctness!
Thank you again to the #1 community for pushing this forward. This week's special shoutout goes to @0x11c11e for some amazing contributions.
What's Changed
- fix unimport ExaSearch when use Exa by @fei0810 in #722
- Multi Agents - Human in the Loop by @assafelovic in #733
- Correct typo in class name HuggingFaceProvider by @wuloi in #735
- moving the sources box above the logs that follow it by @ElishaKay in #738
- Add Support for Multiple Retrievers in GPTR by @0x11c11e in #726
- chore: Update generate_report function to include tone parameter by @0x11c11e in #741
New Contributors
Full Changelog: v3.0.3...v3.0.4
