Use .env variables in docker-compose

.env

@@ -1,4 +1,3 @@
 THREADS=14
 CONTEXT_SIZE=700
-MODEL_PATH=/models
-DEFAULT_MODEL=/models/7B/ggml-vicuna-7b-4bit.bin
+MODELS_PATH=/models

README.md

@@ -19,8 +19,8 @@ cd llama-cli
 # copy your models to models/
 cp your-model.bin models/
 
-# (optional) Edit the .env file to set the number of concurrent threads used for inference
-# echo "THREADS=14" > .env
+# (optional) Edit the .env file to set things like context size and threads
+# vim .env
 
 # start with docker-compose
 docker compose up -d --build

docker-compose.yaml

@@ -2,14 +2,14 @@ version: '3.6'
 
 services:
 
-  chatgpt:
-    image: ghcr.io/mckaywrigley/chatbot-ui:main
-    # platform: linux/amd64
-    ports:
-      - 3000:3000
-    environment:
-      - 'OPENAI_API_KEY=sk-000000000000000'
-      - 'OPENAI_API_HOST=http://api:8080'
+  # chatgpt:
+  #   image: ghcr.io/mckaywrigley/chatbot-ui:main
+  #   # platform: linux/amd64
+  #   ports:
+  #     - 3000:3000
+  #   environment:
+  #     - 'OPENAI_API_KEY=sk-000000000000000'
+  #     - 'OPENAI_API_HOST=http://api:8080'
 
   api:
     # image: quay.io/go-skynet/llama-cli:latest
@@ -19,9 +19,9 @@ services:
     ports:
       - 8080:8080
     environment:
-      - MODELS_PATH=/models
-      - CONTEXT_SIZE=700
-      - THREADS=10
+      - MODELS_PATH=$MODELS_PATH
+      - CONTEXT_SIZE=$CONTEXT_SIZE
+      - THREADS=$THREADS
     volumes:
       - ./models:/models:cached
     command: api