From 2d329d48060df412ef61d494e7ddc72b9ab27d03 Mon Sep 17 00:00:00 2001
From: Pat Wendorf <dungeons@gmail.com>
Date: Fri, 29 Nov 2024 09:08:24 -0500
Subject: [PATCH] Updated instructions for new .env settings

---
 README.md  | 6 ++++--
 sample.env | 4 +---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/README.md b/README.md
index d9b4f98..a311b42 100644
--- a/README.md
+++ b/README.md
@@ -14,9 +14,11 @@ pip install -r requirements.txt
 
 Copy sample.env to .env and point your endpoint URLs for a working llama.cpp and whisper.cpp running in server/api mode.
 
-## llama.cpp and whisper.cpp
+## llama.cpp/ollama and whisper.cpp
 
-These need to be running in server mode somewhere on your local machine or on your network.  Make sure the PROMPT_FORMAT in your .env file matches exactly to what the LLM model expects.
+These need to be running in server mode somewhere on your local machine or on your network.  Add the endpoints to your .env
+
+The default values are correct if you run whisper.cpp and ollama server or llama.cpp server on your local machine.
 
 ## Running
 
diff --git a/sample.env b/sample.env
index 55a6870..e1ada96 100644
--- a/sample.env
+++ b/sample.env
@@ -1,9 +1,7 @@
 WHISPERCPP_URL="http://localhost:8088/inference"
-LLAMACPP_URL="http://localhost:8080/completion"
+LLAMACPP_URL="http://localhost:8080/v1"
 SYSTEM_MESSAGE="You are a friendly chatbot that summarizes call transcripts"
 SUMMARY_PROMPT="Call Transcript: {chunk}\n\nInstruction: Summarize the above call transcript but DO NOT MENTION THE TRANSCRIPT"
 SENTIMENT_PROMPT="Call Transcript: {chunk}\n\nInstruction: Summarize the sentiment for topics in the above call transcript but DO NOT MENTION THE TRANSCRIPT"
-PROMPT_FORMAT="<|im_start|>system\n{system}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
-STOP_TOKEN="<|im_end|>"
 CHUNK_SIZE=12288
 TEMPERATURE=0.1
\ No newline at end of file