modelmix 2.4.2 → 2.4.6

package/README.md

@@ -1,4 +1,4 @@
-# 🧬 ModelMix: Unified API for Diverse AI Language Models
+# 🧬 ModelMix: Unified API for Diverse AI LLM
 
 **ModelMix** is a versatile module that enables seamless integration of various language models from different providers through a unified interface. With ModelMix, you can effortlessly manage and utilize multiple AI models while controlling parallel requests to avoid provider restrictions.
 
@@ -82,32 +82,42 @@ Here's a quick example to get you started:
 
     ```javascript
     console.log("\n" + '--------| gpt-4o |--------');
-    const gpt = mmix.create('gpt-4o', { temperature: 0.5 }).addText("Have you ever eaten a {animal}?");
+    const gpt = mmix.create('gpt-4o', { temperature: 0.5 });
+    gpt.addText("Have you ever eaten a {animal}?");
     gpt.replace({ '{animal}': 'cat' });
     console.log(await gpt.message());
+    ```
 
+    ```javascript
     console.log("\n" + '--------| [writer] claude-3-5-sonnet-20240620 |--------');
     const setup = {
         config: { system: "You are a writer like Stephen King" },
         options: { temperature: 0.5 }
     }
     const writer = mmix.create('claude-3-5-sonnet-20240620', setup);
-    writer.replace({ '{story_title}': 'The Mysterious Package' }) // or claude.replaceKeyFromFile(key, filePath)
+    writer.replace({ '{story_title}': 'The Mysterious Package' })
+    // or write.replaceKeyFromFile('{story_title}', './title.md');
     const story = await writer.addTextFromFile('./prompt.md').message();
     console.log(story);
+    ```
 
+    ```javascript
     console.log("\n" + '--------| [image] claude-3-5-sonnet-20240620 |--------');
     const claude = mmix.create('claude-3-5-sonnet-20240620', { temperature: 0.5 });
     claude.addImage("./watson.jpg"); // or claude.addImageFromUrl(url)
     const imageDescription = await claude.addText("Describe the image").message();
     console.log(imageDescription);
+    ```
 
+    ```javascript
     console.log("\n" + '--------| pplx-70b-online |--------');
     const pplx = mmix.create('pplx-70b-online', { max_tokens: 500 });
     pplx.addText('How much is ETH trading in USD?');
     const news = await pplx.addText('What are the 3 most recent Ethereum news?').message();
     console.log(news);
+    ```
 
+    ```javascript
     console.log("\n" + '--------| ollama (llava:latest) |--------');
     await mmix.create('llava:latest')
         .addImage("./watson.jpg")
@@ -115,7 +125,82 @@ Here's a quick example to get you started:
         .stream((data) => { console.log(data.message); });
     ```
 4. Find the files for this example at: [/ModelMix/demo](https://github.com/clasen/ModelMix/tree/master/demo).
-   
+
+## 🔄 Templating Methods
+
+### `replace` Method
+
+The `replace` method is used to define key-value pairs for text replacement in the messages and system prompt. 
+
+#### Usage:
+```javascript
+gpt.replace({ '{{key1}}': 'value1', '{{key2}}': 'value2' });
+```
+
+#### How it works:
+1. It updates the `config.replace` object with the provided key-value pairs.
+2. In the template, placeholders like `{{key1}}` will be replaced with 'value1'.
+
+#### Example:
+```javascript
+gpt
+  .replace({ '{{name}}': 'Alice', '{{age}}': '30' })
+  .addText('Hello {{name}}, are you {{age}} years old?');
+```
+This would result in the message: "Hello Alice, are you 30 years old?"
+
+### `replaceKeyFromFile` Method
+
+The `replaceKeyFromFile` method is similar to `replace`, but it reads the replacement value from a file.
+
+#### Usage:
+```javascript
+messageHandler.replaceKeyFromFile('longText', './path/to/file.txt');
+```
+
+#### How it works:
+1. It reads the content of the specified file synchronously.
+2. It then calls the `replace` method, using the provided key and the file content as the value.
+
+#### Example:
+```javascript
+messageHandler
+  .replaceKeyFromFile('article_file_contents', './article.txt')
+  .addText('Please summarize this article: article_file_contents');
+```
+This would replace `article_file_contents` with the entire content of 'article.txt'.
+
+### When to use each method:
+- Use `replace` for short, inline replacements or dynamically generated content.
+- Use `replaceKeyFromFile` for longer texts or content that's stored externally.
+
+Both methods allow for flexible content insertion, enabling you to create dynamic and customizable prompts for your AI model interactions.
+
+## 🐛 Enabling Debug Mode
+
+To activate debug mode in ModelMix and view detailed request information, follow these two steps:
+
+1. In the ModelMix constructor, include `debug: true` in the configuration:
+
+   ```javascript
+   const mix = new ModelMix({
+     config: {
+       debug: true
+       // ... other configuration options ...
+     }
+   });
+   ```
+
+2. When running your script from the command line, use the `DEBUG=ModelMix*` prefix:
+
+   ```
+   DEBUG=ModelMix* node your_script.js
+   ```
+
+When you run your script this way, you'll see detailed information about the requests in the console, including the configuration and options used for each AI model request.
+
+This information is valuable for debugging and understanding how ModelMix is processing your requests.
+
 ## 📚 ModelMix Class Overview
 
 ```javascript
@@ -234,81 +319,6 @@ new MixLMStudio(args = { config: {}, options: {} })
     - `url`: The endpoint URL to which the model sends requests.
   - **options**: Default options for Ollama model instances.
 
-## Explanation of `replace` and `replaceKeyFromFile` Methods
-
-### `replace` Method
-
-The `replace` method is used to define key-value pairs for text replacement in the messages and system prompt. 
-
-#### Usage:
-```javascript
-gpt.replace({ '{{key1}}': 'value1', '{{key2}}': 'value2' });
-```
-
-#### How it works:
--  It updates the `config.replace` object with the provided key-value pairs.
--  In the template, placeholders like `{{key1}}` will be replaced with 'value1'.
-
-#### Example:
-```javascript
-gpt
-  .replace({ '{{name}}': 'Alice', '{{age}}': '30' })
-  .addText('Hello {{name}}, are you {{age}} years old?');
-```
-This would result in the message: "Hello Alice, are you 30 years old?"
-
-### `replaceKeyFromFile` Method
-
-The `replaceKeyFromFile` method is similar to `replace`, but it reads the replacement value from a file.
-
-#### Usage:
-```javascript
-messageHandler.replaceKeyFromFile('longText', './path/to/file.txt');
-```
-
-#### How it works:
-1. It reads the content of the specified file synchronously.
-2. It then calls the `replace` method, using the provided key and the file content as the value.
-
-#### Example:
-```javascript
-messageHandler
-  .replaceKeyFromFile('article_file_contents', './article.txt')
-  .addText('Please summarize this article: article_file_contents');
-```
-This would replace `article_file_contents` with the entire content of 'article.txt'.
-
-### When to use each method:
-- Use `replace` for short, inline replacements or dynamically generated content.
-- Use `replaceKeyFromFile` for longer texts or content that's stored externally.
-
-Both methods allow for flexible content insertion, enabling you to create dynamic and customizable prompts for your AI model interactions.
-
-## Enabling Debug Mode in ModelMix
-
-To activate debug mode in ModelMix and view detailed request information, follow these two steps:
-
-1. In the ModelMix constructor, include `debug: true` in the configuration:
-
-   ```javascript
-   const mix = new ModelMix({
-     config: {
-       debug: true
-       // ... other configuration options ...
-     }
-   });
-   ```
-
-2. When running your script from the command line, use the `DEBUG=ModelMix*` prefix:
-
-   ```
-   DEBUG=ModelMix* node your_script.js
-   ```
-
-When you run your script this way, you'll see detailed information about the requests in the console, including the configuration and options used for each AI model request.
-
-This information is valuable for debugging and understanding how ModelMix is processing your requests.
-
 ## 🤝 Contributing
 
 Contributions are welcome! If you find any issues or have suggestions for improvement, please open an issue or submit a pull request on the [GitHub repository](https://github.com/clasen/ModelMix).

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "modelmix",
-  "version": "2.4.2",
-  "description": "🧬 ModelMix - Unified API for Diverse AI Language Models.",
+  "version": "2.4.6",
+  "description": "🧬 ModelMix - Unified API for Diverse AI LLM.",
   "main": "index.js",
   "repository": {
     "type": "git",