Readme fix

README.md

@@ -36,8 +36,9 @@ below.  This has only been tested on Linux, but I think it will work on Windows
    for your operating system.
 2. Install the required Python packages, e.g., by running `pip install -r
    requirements.txt`
-3. For voice recognition, install [Whisper.cpp](https://github.com/ggerganov/whisper.cpp), and after compiling, mode the "libwhisper.so" file to the "glados" folder or add it to your path.  For Windows, check out the discussion in my [whisper pull request](https://github.com/ggerganov/whisper.cpp/pull/1524).
-4.  Download the models:
+3. For the LLM, install [Llama.cpp](https://github.com/ggerganov/llama.cpp), and compile it for your CPU or GPU. Edit the LLAMA_SERVER_PATH parameter in glados.py to match your installation path.
+4. For voice recognition, install [Whisper.cpp](https://github.com/ggerganov/whisper.cpp), and after compiling, mode the "libwhisper.so" file to the "glados" folder or add it to your path.  For Windows, check out the discussion in my [whisper pull request](https://github.com/ggerganov/whisper.cpp/pull/1524).
+5.  Download the models:
     1.  [voice recognition model](https://huggingface.co/distil-whisper/distil-medium.en/resolve/main/ggml-medium-32-2.en.bin?download=true)
     2.  [Llama-3 8B](https://huggingface.co/bartowski/Meta-Llama-3-8B-Instruct-GGUF/resolve/main/Meta-Llama-3-8B-Instruct-IQ3_XS.gguf?download=true) or
     3.  [Llama-3 70B](https://huggingface.co/MaziyarPanahi/Meta-Llama-3-70B-Instruct-GGUF/resolve/main/Meta-Llama-3-70B-Instruct.IQ4_XS.gguf?download=true)

glados.py

@@ -27,7 +27,6 @@
 LLM_MODEL = "Meta-Llama-3-8B-Instruct-Q6_K.gguf"  # This model is smaller and faster, but gets confused more easily
 LLM_STOP_SEQUENCE = "<|eot_id|>"  # End of sentence token for Meta-Llama-3
 LLAMA_SERVER_PATH = "/home/dnhkng/Documents/LLM/llama.cpp"
-LLAMA_SERVER_URL = "http://localhost:8080/v1/chat/completions"
 LLAMA_SERVER_URL = "http://localhost:8080/completion"
 LLAMA_SERVER_HEADERS = {"Authorization": "Bearer your_api_key_here"}
 LLAMA3_TEMPLATE = "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"