fix(install): bump install script node version and update docs

README.md

@@ -71,6 +71,19 @@ genai --profile joe config
 
 All the commands executed with `--profile joe` argument will use that configuration (and default as a fallback).
 
+### Autocompletion
+
+The full commands have many segments due to alignment with the SDK and REST API. The CLI works best with autocompletion. Run the following to activate autocompletion, replace `.zshrc` with the configuration file of your shell:
+
+```bash
+genai completion >> ~/.zshrc
+source ~./zshrc
+```
+
+### Output format
+
+You can choose default output format during `genai config` or set it via `--output-format` flag. Choices are `yaml` and `json`. Former is ideal for direct viewing, latter for piping into [jq](https://jqlang.github.io/jq/).
+
 ## Commands
 
 ```bash

install.sh

@@ -61,7 +61,7 @@ then
         exit 1
     fi
 else
-    MINIMAL="v16.10.0"
+    MINIMAL="v18.18.2"
     DETECTED=$(node -v)
     echo $DETECTED
     RESULT=$(node -e "console.log(\"$DETECTED\".replace('v', '').localeCompare(\"$MINIMAL\".replace('v', ''), undefined, { numeric: true }))")

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ibm-generative-ai/cli",
-  "version": "2.0.0",
+  "version": "2.0.1",
   "description": "CLI for IBM Generative AI (Tech Preview)",
   "keywords": [
     "ai",
@@ -32,7 +32,7 @@
   },
   "packageManager": "yarn@3.5.0",
   "engines": {
-    "node": ">=18.12.0"
+    "node": ">=18.18.2"
   },
   "lint-staged": {
     "*.js": [

src/commands/text/chat/create.js

@@ -8,22 +8,12 @@ export const createCommandDefinition = [
   (yargs) =>
     yargs
       .middleware(clientMiddleware)
-      .middleware(clientMiddleware)
-      .options(generationConfig)
-      .middleware(generationMiddleware)
+      .positional("message", {
+        type: "string",
+        describe: "Content of the message",
+      })
       .options(
         groupOptions({
-          model: {
-            alias: "m",
-            describe: "Select a model to be used for chat",
-            requiresArg: true,
-            type: "string",
-            coerce: (parameters) => {
-              if (typeof parameters !== "string")
-                throw new Error("Only a single model must be specified");
-              return parameters;
-            },
-          },
           conversation: {
             alias: "c",
             type: "string",
@@ -38,10 +28,8 @@ export const createCommandDefinition = [
           },
         })
       )
-      .positional("message", {
-        describe: "",
-        array: true,
-      }),
+      .options(generationConfig)
+      .middleware(generationMiddleware),
   async (args) => {
     const { model, message } = args;
     const output = await args.client.text.chat.create(