Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Commit
•
d1d40ef
1
Parent(s):
4401ddc
Update DESCRIPTION.md
Browse files- DESCRIPTION.md +0 -2
DESCRIPTION.md
CHANGED
|
@@ -1,9 +1,7 @@
|
|
| 1 |
# Development of a Virtual Assistant Powered by the GPT-4 language model
|
| 2 |
-
|
| 3 |
This project is an innovative initiative by [Tall Tree Health](https://www.talltreehealth.ca/) to enhance the customer experience by integrating cutting-edge conversational Artificial Intelligence (AI) technologies. This question-answering (Q&A) chatbot responds to real-time queries, providing users with personalized guidance as they navigate the healthcare landscape offered by Tall Tree. The Retrieval Augmented Generation (RAG) technique is used to improve the accuracy and reliability of chatbot responses by fetching relevant and up-to-date information from the Tall Tree database.
|
| 4 |
|
| 5 |
# Chatbot Application Development Overview
|
| 6 |
-
|
| 7 |
The application has been developed in pure Python. The back-end architecture has been built using [LangChain](https://github.com/langchain-ai/langchain), while the front-end, i.e., the chat interface, has been created with [Streamlit](https://streamlit.io/). At the core of our chatbot lies [OpenAI's GPT-4](https://openai.com/gpt-4) (Generative Pre-trained Transformer 4), a state-of-the-art language model known for its advanced comprehension and generation capabilities. For storage of the embeddings and efficient similarity search, the [Qdrant](https://qdrant.tech/) vector database is used. LangChain offers seamless integration with both the OpenAI API and Qdrant, ensuring a smooth workflow.
|
| 8 |
|
| 9 |
## Note:
|
|
|
|
| 1 |
# Development of a Virtual Assistant Powered by the GPT-4 language model
|
|
|
|
| 2 |
This project is an innovative initiative by [Tall Tree Health](https://www.talltreehealth.ca/) to enhance the customer experience by integrating cutting-edge conversational Artificial Intelligence (AI) technologies. This question-answering (Q&A) chatbot responds to real-time queries, providing users with personalized guidance as they navigate the healthcare landscape offered by Tall Tree. The Retrieval Augmented Generation (RAG) technique is used to improve the accuracy and reliability of chatbot responses by fetching relevant and up-to-date information from the Tall Tree database.
|
| 3 |
|
| 4 |
# Chatbot Application Development Overview
|
|
|
|
| 5 |
The application has been developed in pure Python. The back-end architecture has been built using [LangChain](https://github.com/langchain-ai/langchain), while the front-end, i.e., the chat interface, has been created with [Streamlit](https://streamlit.io/). At the core of our chatbot lies [OpenAI's GPT-4](https://openai.com/gpt-4) (Generative Pre-trained Transformer 4), a state-of-the-art language model known for its advanced comprehension and generation capabilities. For storage of the embeddings and efficient similarity search, the [Qdrant](https://qdrant.tech/) vector database is used. LangChain offers seamless integration with both the OpenAI API and Qdrant, ensuring a smooth workflow.
|
| 6 |
|
| 7 |
## Note:
|