add vscode devcontainer and launch task

.devcontainer/devcontainer.json

@@ -0,0 +1,48 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/docker-existing-docker-compose
+{
+	"name": "Existing Docker Compose (Extend)",
+
+	// Update the 'dockerComposeFile' list if you have more compose files or use different names.
+	// The .devcontainer/docker-compose.yml file contains any overrides you need/want to make.
+	"dockerComposeFile": [
+		"../docker-compose.yaml",
+		"docker-compose.yml"
+	],
+
+	// The 'service' property is the name of the service for the container that VS Code should
+	// use. Update this value and .devcontainer/docker-compose.yml to the real service name.
+	"service": "api",
+
+	// The optional 'workspaceFolder' property is the path VS Code should open by default when
+	// connected. This is typically a file mount in .devcontainer/docker-compose.yml
+	"workspaceFolder": "/workspaces",
+	"features": {
+		"ghcr.io/devcontainers/features/go:1": {
+			"version": "latest"
+		}
+	},
+
+	"overrideCommand": true
+	
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Uncomment the next line if you want start specific services in your Docker Compose config.
+	// "runServices": [],
+
+	// Uncomment the next line if you want to keep your containers running after VS Code shuts down.
+	// "shutdownAction": "none",
+
+	// Uncomment the next line to run commands after the container is created.
+	// "postCreateCommand": "cat /etc/os-release",
+
+	// Configure tool-specific properties.
+	// "customizations": {},
+
+	// Uncomment to connect as an existing user other than the container default. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "devcontainer"
+}

.devcontainer/docker-compose.yml

@@ -0,0 +1,26 @@
+version: '3.6'
+services:
+  # Update this to the name of the service you want to work with in your docker-compose.yml file
+  api:
+    # Uncomment if you want to override the service's Dockerfile to one in the .devcontainer 
+    # folder. Note that the path of the Dockerfile and context is relative to the *primary* 
+    # docker-compose.yml file (the first in the devcontainer.json "dockerComposeFile"
+    # array). The sample below assumes your primary file is in the root of your project.
+    #
+    # build:
+    #   context: .
+    #   dockerfile: .devcontainer/Dockerfile
+
+    volumes:
+      # Update this to wherever you want VS Code to mount the folder of your project
+      - .:/workspaces:cached
+
+    # Uncomment the next four lines if you will use a ptrace-based debugger like C++, Go, and Rust.
+    # cap_add:
+    #   - SYS_PTRACE
+    # security_opt:
+    #   - seccomp:unconfined
+
+    # Overrides default command so things don't shut down after the process ends.
+    command: sleep infinity
+ 

.dockerignore

@@ -1 +1 @@
-models/*.bin
+models

.env

@@ -1 +1,3 @@
-THREADS=14
+THREADS=14
+CONTEXT_SIZE=700
+MODEL_PATH=/models

.gitignore

@@ -1,2 +1,16 @@
+# go-llama build artifacts
+go-llama.cpp
+binding.o
+libbinding.a
+
+# llama models
+models
+
+# llama-cli build binary
 llama-cli
-models/*.bin
+
+# make test reports
+checkstyle-report.xml 
+profile.cov
+coverage.xml
+yamllint-checkstyle.xml

.vscode/launch.json

@@ -0,0 +1,20 @@
+{
+    "version": "0.2.0",
+    "configurations": [
+    
+    {
+        "name": "Launch Go",
+        "type": "go",
+        "request": "launch",
+        "mode": "debug",
+        "program": "${workspaceFolder}/main.go",
+        "args": [
+            "api",
+            "--models-path",
+            "/models/13B",
+            "--default-model",
+            "/models/13B/ggml-gpt4-x-alpaca-native-13b-q4_1.bin"
+        ]
+    }
+    ]
+}

Dockerfile

@@ -16,4 +16,5 @@ RUN C_INCLUDE_PATH=/build/go-llama.cpp LIBRARY_PATH=/build/go-llama.cpp go build
 
 FROM debian:$DEBIAN_VERSION
 COPY --from=builder /build/llama-cli /usr/bin/llama-cli
-ENTRYPOINT [ "/usr/bin/llama-cli" ]
+ENTRYPOINT [ "/usr/bin/llama-cli" ]
+CMD [ "sleep", "infinity" ]

docker-compose.yaml

@@ -1,15 +1,28 @@
 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'
+
   api:
     image: quay.io/go-skynet/llama-cli:latest
-    build: .
-    volumes:
-      - ./models:/models
+    build:
+      context: .
+      dockerfile: Dockerfile
     ports:
-      - 8080:8080
+      - 3001:8080
     environment:
-      - MODELS_PATH=/models
-      - CONTEXT_SIZE=700
+      - MODELS_PATH=$MODELS_PATH
+      - CONTEXT_SIZE=$CONTEXT_SIZE
       - THREADS=$THREADS
-    command: api
+    volumes:
+      - ./models/:/models:cached
+    command: api
+