Releases: assafelovic/gpt-researcher
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
Contributors
Assets 2
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!
Stability and Poetry support 🎉
Excited to introduce latest version that removes strict dependencies from requirements.txt, fixes some installation issues and adds support for virtual env and Poetry!
Big shoutout to contributors @aaaastark for the PR: #319
Quick installation fix
Releasing new version that resolves dependency issues with latest version.
New features and stability 🎉
Excited to kick off the new year with a long awaited feature: Research report on specific urls! 🎉
You can now skip the search by providing urls directly to GPTResearcher and create a research report like so:
urls = ["https://docs.tavily.com/docs/tavily-api/introduction",
"https://docs.tavily.com/docs/tavily-api/python-sdk",
"https://docs.tavily.com/docs/tavily-api/rest_api"]
query = "How can I integrate Tavily Rest API with my application?"
async def get_report(query: str, source_urls: list) -> str:
researcher = GPTResearcher(query=query, source_urls=source_urls)
report = await researcher.run()
return report
report = asyncio.run(get_report(query, urls))
print(report)
The release includes additional stability and performance improvements, along with updated library dependencies.