Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,86 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
<div align="center">
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
<h1 style="">Welcome to Brief.AI</h1>
|
| 16 |
+
</div>
|
| 17 |
+
|
| 18 |
+
Brief.AI is an innovative platform tailored to hedge funds and investment banks, revolutionizing insights into
|
| 19 |
+
earnings calls by harnessing large language models.
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
<h1 style="">🤔 Who is Brief.AI?</h1>
|
| 25 |
+
|
| 26 |
+
Our platform aims to be the voice for any executive or analyst on the buy side or sell-side trying to analyze earning call transcripts through two products:
|
| 27 |
+
|
| 28 |
+
💬 **[Javi - Question Answering over Earnings Call Transcript](https://github.com/brief-ai-uchicago/Javi-The-Earnings-Call-Expert)**
|
| 29 |
+
* The intelligent chatbot can engage in real-time queries regarding specific details from earnings call transcripts. This elevates user experience, ensuring immediate access to critical information without manual data trawling.
|
| 30 |
+
|
| 31 |
+
📃 **[Long-Short - KPI Extractor](https://github.com/brief-ai-uchicago/LongShort)**
|
| 32 |
+
* This model efficiently extracts crucial performance indicators and financial metrics
|
| 33 |
+
from a comprehensive collection of earnings call transcripts.
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
<h1 style="">🚀 What can this help with?</h1>
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
💬 **[Chatbot for Earnings Calls:](https://github.com/brief-ai-uchicago/Javi-The-Earnings-Call-Expert)**
|
| 42 |
+
|
| 43 |
+
Our chatbot amplifies the functionality of large language models, empowering users to engage in interactive conversations with earnings calls. This versatile tool serves multiple purposes, such as:
|
| 44 |
+
|
| 45 |
+
- 🤖 *Comparison across multiple documents*
|
| 46 |
+
|
| 47 |
+
- The chatbot uses an agent to compare queries that retrieves multiple documents and is able to create a chain of thought reasoning chain to answer queries.
|
| 48 |
+
|
| 49 |
+
- 🧠 *Memory:*
|
| 50 |
+
|
| 51 |
+
- Memory refers to persisting state between calls of a large language model. You can continue to ask follow-up questions from initial queries without restating the context.
|
| 52 |
+
|
| 53 |
+
- ⚡ *Punctual Information:*
|
| 54 |
+
|
| 55 |
+
- The chatbot provides quick and precise responses to specific questions, making it ideal for extracting timely information from earnings calls.
|
| 56 |
+
|
| 57 |
+
- 🚨 *Sentiment Analysis:*
|
| 58 |
+
|
| 59 |
+
- Users can gauge the sentiment and emotional tone of earnings calls, helping them make more informed investment decisions.
|
| 60 |
+
|
| 61 |
+
📃 **[Detailed Earnings Calls Analysis:](https://github.com/brief-ai-uchicago/LongShort)**
|
| 62 |
+
|
| 63 |
+
- 📚 Concise answers
|
| 64 |
+
|
| 65 |
+
- Utilizing cutting-edge language models, our system delivers succinct, structured answers extracted from verbose earnings call transcripts, streamlining the distillation of key performance indicators (KPIs) for analysts and executives.
|
| 66 |
+
|
| 67 |
+
- 🧐 Effective KPI extraction from long transcripts
|
| 68 |
+
|
| 69 |
+
- Extracting data from unstructured sources like PDFs has become crucial for businesses, researchers, and individuals. Traditional manual methods are slow and error-prone, necessitating more efficient alternatives.
|
| 70 |
+
|
| 71 |
+
For more detailed information on these capabilities and concepts, please refer to our comprehensive product documentation.
|
| 72 |
+
|
| 73 |
+
<h1 style="">📖 Documentation</h1>
|
| 74 |
+
For a complete guide to the documentation, please follow the steps outlined below to navigate through the GitHub organization:
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
* [Javi-The-Earnings-Call-Expert](https://github.com/brief-ai-uchicago/Javi-The-Earnings-Call-Expert): Chatbot powered by langchain.
|
| 78 |
+
|
| 79 |
+
* [LongShort-Dataset](https://github.com/brief-ai-uchicago/LongShort-Dataset): This is the dataset utilized for fine-tuning.
|
| 80 |
+
|
| 81 |
+
* [LongShort](https://github.com/brief-ai-uchicago/LongShort): Fine-tuned models designed for KPI (Key Performance Indicators) extraction from earnings call transcripts.
|
| 82 |
+
|
| 83 |
+
* [Website](https://github.com/brief-ai-uchicago/Brief-AI): Platform's UI/UX.
|
| 84 |
+
|
| 85 |
+
* [Branding](https://github.com/brief-ai-uchicago/Branding): Repository containing branding documentation and assets.
|
| 86 |
+
|
| 87 |
+
## <h1 style=""> 🚀 Your Next Stop</h1>
|
| 88 |
+
|
| 89 |
+
* [Javi-The-Earnings-Call-Expert](https://github.com/brief-ai-uchicago/Javi-The-Earnings-Call-Expert): Chatbot powered by langchain.
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
|