v3.1.6

Another release of performance improvements and bug fixes. Welcome @kga245 as a new contributor with a super valuable contribution and special shoutout again to @winsonluk for helping improve GPTR's stability!

What's Changed

• Fix xAI bug by @winsonluk in #1021
• added language support by @assafelovic in #1026
• fix: Add language parameter support to generate_subtopic_report_prompt by @onlydole in #1029
• Fix generate_custom_report_prompt language bug by @winsonluk in #1033
• Introduce strategic_token_limit to fix Anthropic bug by @winsonluk in #1032
• Feature: unified logs handler by @kga245 in #1031

New Contributors

• @kga245 made their first contribution in #1031

Full Changelog: v3.1.5...v3.1.6

v3.1.5

Welcome to all the new contributors and special shoutout to @winsonluk! This release includes critical bug fixes and improvements to report quality such as ranking sources and content before generation. This release is recommended for all!

What's Changed

• Adding a ranking step of research sources by @assafelovic in #992
• UX Fixes by @ElishaKay in #994
• Fix max_results for Google Search by @winsonluk in #1009
• Add xAI by @winsonluk in #1017
• Fix uncaught exception in Google retrieval by @winsonluk in #1018
• Default to the retriever set in config rather than just tavily by @winsonluk in #1019
• 【feature】Commit Message: Optimized PyMuPDFScraper to handle invalid o… by @MC-shark in #1012
• Add support for DashScope provider in LLM and embeddings modules by @AStupidBear in #1013
• Fix AWS Bedrock invocation; create output folder in cli.py if it doesn't exist by @ai-1st in #1014

New Contributors

• @winsonluk made their first contribution in #1009
• @MC-shark made their first contribution in #1012
• @AStupidBear made their first contribution in #1013
• @ai-1st made their first contribution in #1014

Full Changelog: v3.1.4...v3.1.5

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

• @roninio made their first contribution in #979

Full Changelog: v3.1.3...v3.1.4

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 getHost reference 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 temperature and max_tokens in create_chat_completion by @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