Updated README

README.md

@@ -729,40 +729,70 @@ docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/lla
 
 [Docker on termux (requires root)](https://gist.github.com/FreddieOliveira/efe850df7ff3951cb62d74bd770dce27) is currently the only known way to run this on phones, see [termux support issue](https://github.com/abetlen/llama-cpp-python/issues/389)
 
-# SeKernel_for_LLM
-This is a Python module used to create memory in your chat applications.
+# 🃏 SeKernel_for_LLM
+This is a Python module used to create a semantic kernel in your openai api compatible chat applications.
+
+### 🍬 Features
+- In-chat memory
+- Internet-search
+- Database querying
 
 ## ⚙️ How to:
-- Clone the repo and import the module into your project. Ensure that it is in the project directory.
-- https://github.com/perpendicularai/SeKernel_for_LLM
-- ```
+- Clone the repo and import the modules into your project. Ensure that it is in the project directory.
+- ```python
   import kernel
+  import plugins
+
+  ### INTERNET-SEARCH ###
+  - Define search plugin
+  search_prompt = plugins.searchPlugin(output=question) # If context equals None, use the Chat template. See `kernel.py` for more templates.
+
+  - Initialize the kernel
+  data = kernel.shopTemplate(prompt=prompt, plugin=plugins.defaultPlugin(), context=search_prompt or context=None # Where no context is provided, and so you may assume the AI assistant to not have any awareness of information of events that took place after the date until which it's training data is up until) # See plugins.py module for more plugins
+
+  ### DATABASE ###
+  - Using this database plugin
+  -- Initialize the database plugin
+  db = plugins.dbConn()
 
-  # Initialize the kernel
-  data = kernel
+  - Use the database plugin along with the dbChatPlugin
+  data = kernel.chatTemplate(prompt=prompt, plugin=plugins.dbChatPlugin())
 
-  # Create a template
-  data = [
-    {"role": "system", "content": """You are an intelligent assistant. You always provide well-reasoned answers that are both correct and helpful."""},
-    {"role": "user", "content": question},
-  ]
+  - Excuting the query
+  db.execute(response)
 
-  # Set messages parameter equal to data. Depending on your LLM API defintion, messages may be a different parameter, in this case it is messages, as defined in the OpenAI API definition.
-  messages = data
+  - Getting the output
+  response = db.fetchall()
+
+  ### LlamaCpp ###
+  - Parsing the kernel model to LlamaCpp
+  LlamaCpp
+  client = Llama(
+        model_path=kernel.model() # Make sure to add your GGUF model in the kernel module.
+  )
+
+  - Use the kernel and set messages parameter equal to data. Depending on your LLM API defintion, messages may be a different parameter, in this case it is messages, as defined in the OpenAI API definition.
+  output = client.create_chat_completions(
+    messages = data
+  )
   ```
   See [OpenAI](https://platform.openai.com/docs/api-reference/chat/create) API reference for more.
-
-  ```
-  # You may then append any new content and/or messages to the kernel
+- ```
+  - You may then append any new content and/or messages to the kernel
   data.append(new_message)
   ```
 ## 📽️ Short Films
-See an example of using the SeKernel_for_LLM with 🦙 [LlamaCpp Python bindings](https://github.com/abetlen/llama-cpp-python)
+See examples of using the SeKernel_for_LLM with 🦙 [LlamaCpp Python bindings](https://github.com/abetlen/llama-cpp-python)
 
+#### The square-root of 2
 https://github.com/user-attachments/assets/cb48e962-2cba-4672-b4e7-c0f77455bb74
 
+#### Internet search with Google for the price of leggings
+https://github.com/user-attachments/assets/fdf5ac16-c8b7-4b39-b91b-d4e2d8d2d888
+
+#### Database query
+https://github.com/user-attachments/assets/ad9c87a4-475f-4ca0-a576-109709ca84b0
 
-🍾 I hope this helps someone starting out. Happy prompting!!!
 
 ## Low-level API