updated readme

README.md

@@ -11,3 +11,34 @@ license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+
+# Setup
+
+1. Clone this repo
+2. Create and activate a new virtual environment, using either `conda` or `venv`
+
+    > [Tutorial for setting up virtual environments 🔗](https://www.perplexity.ai/search/how-to-make-GnFc09yGTvSyka0ZWqhSQg?s=c)
+
+3. Make a .env file, for storing api credentials, currently using these 4 credentials.
+   ```
+   HF_TOKEN = ...
+   GOOGLE_SEARCH_ENGINE_ID = ...
+   GOOGLE_SEARCH_API_KEY = ...
+   BING_SEARCH_API_KEY = ...
+   
+   ``` 
+
+4. Install requirements using
+    ```
+    pip install -r requirements.txt --user
+    ```
+5. Startup streamlit server by using
+    ```
+    streamlit run app.py
+    ```
+    or 
+    ```
+    python -m streamlit run app.py
+    ```
+

app.py

@@ -5,6 +5,10 @@ from utils import gen_augmented_prompt_via_websearch, inital_prompt_engineering_
 
 
 COST_PER_1000_TOKENS_USD = 0.139 * 80
+
+# Not using BPE tokenizer to calculate exact number of tokens,
+# using the formula n_tokens =  len(reponse + prompt) * 1.25
+
 CHAT_BOTS = {
     "Mixtral 8x7B v0.1": "mistralai/Mixtral-8x7B-Instruct-v0.1",
     "Mistral 7B v0.1": "mistralai/Mistral-7B-Instruct-v0.1",