abetlen
diff --git a/‎README.md
Copy file name to clipboardExpand all lines: README.md
+35Lines changed: 35 additions & 0 deletions b/‎README.md
Copy file name to clipboardExpand all lines: README.md
+35Lines changed: 35 additions & 0 deletions
@@ -20,6 +20,7 @@ This package provides:
     - OpenAI-like API
     - [LangChain compatibility](https://python.langchain.com/docs/integrations/llms/llamacpp)
     - [LlamaIndex compatibility](https://docs.llamaindex.ai/en/stable/examples/llm/llama_2_llama_cpp.html)
+    - Chat with kernel memory
 - OpenAI compatible web server
     - [Local Copilot replacement](https://llama-cpp-python.readthedocs.io/en/latest/server/#code-completion)
     - [Function Calling support](https://llama-cpp-python.readthedocs.io/en/latest/server/#function-calling)
@@ -704,6 +705,40 @@ 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.
+
+## ⚙️ How to:
+- Clone the repo and import the module into your project. Ensure that it is in the project directory.
+- ```
+  import kernel
+
+  # Initialize the kernel
+  data = kernel
+
+  # 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},
+  ]
+
+  # 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
+  ```
+  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
+  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)
+
+https://github.com/user-attachments/assets/cb48e962-2cba-4672-b4e7-c0f77455bb74
+
+
+🍾 I hope this helps someone starting out. Happy prompting!!!
+
 ## Low-level API
 
 [API Reference](https://llama-cpp-python.readthedocs.io/en/latest/api-reference/#low-level-api)