Releases: assafelovic/gpt-researcher
Stability improvements
What's Changed
- Update introduction.md fixing broken link by @AADaoud in #606
- update on using json_repair from the author of json_repair, thanks! by @pfrench42 in #607
- extract_headers() was throwing an exception when it was examining a l… by @pfrench42 in #610
- Implement more graceful JSON handling on choose_agent in master/actions.py by @AADaoud in #616
New Contributors
Full Changelog: v.0.2.6...v0.2.7
Contributors
Assets 2
v.0.2.6
This release includes additional stability and performance improvements. In addition, excited to support custom retrievers - Custom retrievers allow you to use any search engine that provides an API to retrieve documents and is widely used for enterprise research tasks. Thanks again to the amazing community for all the contributions!
What's Changed
- change deployment name to model to fix the init of the azureopenai model by @xiepei1 in #594
- use repair_json() on output of sub_queries to stop exceptions on local models by @pfrench42 in #596
- fix: similarity_threshold config by @gkhngyk in #597
- Lazily import langchain-huggingface to avoid obligatory install by @ldorigo in #599
- added implementation for custom retriever by @assafelovic in #602
New Contributors
- @xiepei1 made their first contribution in #594
- @pfrench42 made their first contribution in #596
Full Changelog: v.0.2.5...v.0.2.6
Stability improvements
What's Changed
- Add narrower langchain package constraints by @baskaryan in #547
- Fix issue with custom_report in write_report method by @mowkalim in #551
- Feature/gptr pip improvements by @assafelovic in #552
- resolve the issue with the make command not being found when loading docker container by @ElishaKay in #554
- Read the correct variable name in together.py by @fei0810 in #556
- Fix[readme]: Page Not Found by @gkhngyk in #559
- actions.py: Fix typo by @refeed in #572
- finalized default search by @assafelovic in #582
- Update google.py by @gkhngyk in #583
- RFC: generic llm provider by @baskaryan in #546
New Contributors
- @baskaryan made their first contribution in #547
- @mowkalim made their first contribution in #551
- @fei0810 made their first contribution in #556
- @gkhngyk made their first contribution in #559
- @refeed made their first contribution in #572
Full Changelog: v0.2.4...v.0.2.5
LLMs support 🤖
Excited for yet another HUGE release that includes LLM support for the following: Llama3, Mistral, Anthropic, HuggingFace, Together AI, Gemini and more!
We've also updated our docs including examples:
- Customizing the research assistant: https://docs.gptr.dev/docs/gpt-researcher/config
- Configuring LLMs: https://docs.gptr.dev/docs/gpt-researcher/llms
This release also includes LangGraph deployment by @hwchase17 and additional stability improvements. Thank you to all the amazing contributions!
What's Changed
- remove DOC_Path from docker-compose - rely on .env instead by @ElishaKay in #509
- Adding one-click deploy button for RepoCloud.io to README.md by @cosark in #515
- Fix Pydantic validation of base_url assignment for ChatOpenAI model by @mmashnev in #512
- Added Instructions for Groq by @dphiggs01 in #536
- Implemented GroqProvider by @dphiggs01 in #526
- add support for custom openai api embeddings by @sebaxzero in #528
- langgraph deploy by @hwchase17 in #537
- Add logo to README by @assafelovic in #540
- added pandas dependency for reading csv, commented testing dependenci… by @ElishaKay in #541
- Adding support for Ollama (both LLM and embeddings) by @gschmutz in #527
New Contributors
- @cosark made their first contribution in #515
- @mmashnev made their first contribution in #512
- @sebaxzero made their first contribution in #528
- @gschmutz made their first contribution in #527
Full Changelog: v0.2.3...v0.2.4
Research Local Documents 📄🤯
Research with your local documents 🤯
Excited to finally release GPT Researcher support with local documents! This feature is long overdue and includes support for almost any type of local document such as pdf, text, docx, pptx, csv, xls, md and more! Simply drop your folder dir path as env variable and watch the magic!
This feature also adds support for the local UI, however due to vanilla JS limitations it's still not the optimal UX. We plan to add a React based UI which will include improved UX for local documents.
Lastly, this release includes some additional stability fixes, new and improved documentation and support for Serper Search API! Thanks to the amazing community for this incredible release and special shoutout to @ElishaKay and @proy9714 !
What's Changed
- Update trobuleshooting doc to handle installation bugs related to lib… by @satishjasthi in #497
- Implemented SerpApiSearch Class and removed raise NotImplementedError… by @dphiggs01 in #498
- SerperSearch Class updates 1. max_results param is now used. 2. timeo… by @dphiggs01 in #499
- Feature/new docs by @assafelovic in #507
- Research with local documents by @ElishaKay and @proy9714 in #452
New Contributors
- @satishjasthi made their first contribution in #497
- @dphiggs01 made their first contribution in #498
Full Changelog: v.0.2.2...v0.2.3
Stability improvements 💪
What's Changed
- Added ability to use custom base_url by @arsaboo in #471
- Update README.md by @KPCOFGS in #473
- corrected documentation for pip-usage by @domci in #476
- Update README.md by @assafelovic in #479
- fix flask example error by @Beichen-Ma in #481
- modified to new cheaper OpenAI embedding by @assafelovic in #483
- Feature/verbose by @assafelovic in #485
New Contributors
- @arsaboo made their first contribution in #471
- @KPCOFGS made their first contribution in #473
- @domci made their first contribution in #476
- @Beichen-Ma made their first contribution in #481
Full Changelog: v0.2.1...v.0.2.2
Multi Agent Research 🔎👨👦👦
This is one of the most exciting releases yet. Proud to introduce the latest GPTR x LangGraph integration showcasing the power of flow engineering and multi agent collaboration! Check out the full implementation in the new directory multi_agents.
By using LangGraph, the research process can be significantly improved in depth and quality by leveraging multiple agents with specialized skills. Inspired by the recent STORM paper, this example showcases how a team of AI agents can work together to conduct research on a given topic, from planning to publication. An average run generates a 5-6 page research report in multiple formats such as PDF, Docx and Markdown.
The Multi Agent Team
The research team is made up of 7 AI agents:
- Chief Editor - Oversees the research process and manages the team. This is the "master" agent that coordinates the other agents using Langgraph.
- Researcher (gpt-researcher) - A specialized autonomous agent that conducts in depth research on a given topic.
- Editor - Responsible for planning the research outline and structure.
- Reviewer - Validates the correctness of the research results given a set of criteria.
- Revisor - Revises the research results based on the feedback from the reviewer.
- Writer - Responsible for compiling and writing the final report.
- Publisher - Responsible for publishing the final report in various formats.
Architecture
Detailed reports 🤯🚀
Super excited to share the latest release, highly contributed by the the one and only @proy9714 👏
Introducing long and detailed reports, with a completely new architecture inspired by the latest STORM paper.
In this method we do the following:
- Trigger Initial GPT Researcher report based on task
- Generate subtopics from research summary
- For each subtopic the headers of the subtopic report are extracted and accumulated
- For each subtopic a report is generated making sure that any information about the headers accumulated until now are not re-generated.
- An additional introduction section is written along with a table of contents constructed from the entire report.
- The final report is constructed by appending these : Intro + Table of contents + Subsection reports
In addition, this release includes support for Azure OpenAI @norrisp90
Gemini and Docx support! 🎉
New embeddings, pdf styling and newspaper3k support 👨👨👦👦
Another great release thanks to the amazing community! ❤️
Big shoutout to the following contributions:
@proy9714 for adding newpaper3k support for better article scraping #365
@jimmylin0979 for adding support for additional embeddings such as Mistral, Ollama and HuggingFace #375
@assafelovic adding support for pdf styling of research reports #396
@WarrenTheRabbit for fixing a documentation typo #391
Thank you to everyone and looking forward for more contributions!
