Gpt-researcher

Added improved stability, Docker support and more updated libraries.

This release includes the initial alpha development of the GPT Researcher. The alpha version includes both client (HTML) and backend (FastAPI) support for better customizability.

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](https://python.langchain.com/docs/langgraph/), the research process can be significantly improved in depth and quality by leveraging multiple agents with specialized skills. Inspired by the recent [STORM](https://arxiv.org/abs/2402.14207) 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
<div align="center">
<img align="center" height="600" src="https://cowriter-images.s3.amazonaws.com/gptr-langgraph-architecture.png">
</div>
<br clear="all"/>

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](https://arxiv.org/abs/2402.14207) paper.

In this method we do the following:

1. Trigger Initial GPT Researcher report based on task
2. Generate subtopics from research summary
3. For each subtopic the headers of the subtopic report are extracted and accumulated
4. For each subtopic a report is generated making sure that any information about the headers accumulated until now are not re-generated.
5. An additional introduction section is written along with a table of contents constructed from the entire report.
6. The final report is constructed by appending these : Intro + Table of contents + Subsection reports

In addition, this release includes support for Azure OpenAI norrisp90

v.0.1.6
This release is largely thanks to proy9714 for some high impact contributions!
1. Support for downloading research as docx file https://github.com/assafelovic/gpt-researcher/pull/403
2. Support for Gemini provider https://github.com/assafelovic/gpt-researcher/pull/408
3. Improved report generation with hyperlinks https://github.com/assafelovic/gpt-researcher/pull/404
4. Support for Python3.10 https://github.com/assafelovic/gpt-researcher/pull/403

Huge shoutout to proy9714 👏

Another great release thanks to the amazing community! ❤️

Big shoutout to the following contributions:
proy9714 for adding newpaper3k support for better article scraping https://github.com/assafelovic/gpt-researcher/pull/365
jimmylin0979 for adding support for additional embeddings such as Mistral, Ollama and HuggingFace https://github.com/assafelovic/gpt-researcher/pull/375
assafelovic adding support for pdf styling of research reports https://github.com/assafelovic/gpt-researcher/pull/396
WarrenTheRabbit for fixing a documentation typo https://github.com/assafelovic/gpt-researcher/pull/391

Thank you to everyone and looking forward for more contributions!