Commit
•
a586ea0
1
Parent(s):
fb288e6
Update README.md
Browse files
README.md
CHANGED
@@ -19,6 +19,7 @@ The primary goal of this project is to enhance the user experience by enabling a
|
|
19 |
|
20 |
### Key Features:
|
21 |
- **RAG Framework:** Retrieval Augmented Generation Framework has been implemented to get the relevent context related to queries that deals with referring a particular cell number, or with queries asking follow-up questions with respect to previous responses from the model.
|
|
|
22 |
- **Context-Aware Responses:** By analyzing the code and content in the notebook, the chatbot provides contextually relevant answers.
|
23 |
|
24 |
## Usage
|
@@ -30,6 +31,7 @@ Upload your Jupyter Notebook and start asking questions. Examples for the questi
|
|
30 |
- Before uploading your notebook, make sure that the output of the cells are cleared, as it can cause errors occasionally.
|
31 |
- If the notebook has MarkDown cells, it can sometime disturb the order of the cells that the model gets as context for answering the query,
|
32 |
so it's better to avoid MarkDown cells if any.
|
|
|
33 |
- The context has been provided in a way to answer the queries by just referring the cell number, But sometimes it might not be accurate to pick up the right cell number.
|
34 |
|
35 |
|
|
|
19 |
|
20 |
### Key Features:
|
21 |
- **RAG Framework:** Retrieval Augmented Generation Framework has been implemented to get the relevent context related to queries that deals with referring a particular cell number, or with queries asking follow-up questions with respect to previous responses from the model.
|
22 |
+
- **Prompt Engineering:** The Prompts are written in a way to utilize the contexts properly and correctly to answer the query.
|
23 |
- **Context-Aware Responses:** By analyzing the code and content in the notebook, the chatbot provides contextually relevant answers.
|
24 |
|
25 |
## Usage
|
|
|
31 |
- Before uploading your notebook, make sure that the output of the cells are cleared, as it can cause errors occasionally.
|
32 |
- If the notebook has MarkDown cells, it can sometime disturb the order of the cells that the model gets as context for answering the query,
|
33 |
so it's better to avoid MarkDown cells if any.
|
34 |
+
- Do not have more than 4 line breaks in between the code in a notebook cell, as it leads to partition of code, sometimes resulting in improper context.
|
35 |
- The context has been provided in a way to answer the queries by just referring the cell number, But sometimes it might not be accurate to pick up the right cell number.
|
36 |
|
37 |
|