TS SDK polish

2_typescript/2_llm-prediction/completion.md

@@ -62,10 +62,10 @@ You can also print prediction metadata, such as the model used for generation, n
     TypeScript:
       language: typescript
       code: |
-        console.info("Model used:", prediction.modelInfo.displayName);
-        console.info("Predicted tokens:", prediction.stats.predictedTokensCount);
-        console.info("Time to first token (seconds):", prediction.stats.timeToFirstTokenSec);
-        console.info("Stop reason:", prediction.stats.stopReason);
+        console.info("Model used:", completion.modelInfo.displayName);
+        console.info("Predicted tokens:", completion.stats.predictedTokensCount);
+        console.info("Time to first token (seconds):", completion.stats.timeToFirstTokenSec);
+        console.info("Stop reason:", completion.stats.stopReason);
 ```
 
 ## Example: Get an LLM to Simulate a Terminal

2_typescript/2_llm-prediction/image-input.md

@@ -43,15 +43,15 @@ Use the `client.files.prepareImage()` method to get a handle to the image you ca
 
 ```
 
-If you only have the image in the form of a base64 string, you can use the `client.files.prepareImage64()` method instead.
+If you only have the image in the form of a base64 string, you can use the `client.files.prepareImageBase64()` method instead.
 
 ```lms_code_snippet
   variants:
     Example:
       language: typescript
       code: |
         const imageBase64 = "Your base64 string here";
-        const image = await client.files.prepareImage64(imageBase64);
+        const image = await client.files.prepareImageBase64(imageBase64);
 ```
 
 We support JPEG, PNG, and WebP image formats.
@@ -65,7 +65,7 @@ Generate a prediction by passing the image to the model in the `.respond()` meth
     Example:
       language: typescript
       code: |
-        const prediction = llm.respond([
+        const prediction = model.respond([
           { role: "user", content: "Describe this image please", images: [image] },
         ]);
 ```

2_typescript/2_llm-prediction/parameters.md

@@ -51,7 +51,9 @@ The `.model()` retrieves a handle to a model that has already been loaded, or lo
         const model = await client.llm.model("qwen2.5-7b-instruct", {
           config: {
             contextLength: 8192,
-            gpuOffload: 0.5,
+            gpu: {
+              ratio: 0.5,
+            },
           },
         });
 ```
@@ -70,7 +72,9 @@ The `.load()` method creates a new model instance and loads it with the specifie
         const model = await client.llm.load("qwen2.5-7b-instruct", {
           config: {
             contextLength: 8192,
-            gpuOffload: 0.5,
+            gpu: {
+              ratio: 0.5,
+            },
           },
         });
 ```

2_typescript/2_llm-prediction/structured-response.md

@@ -103,15 +103,7 @@ const schema = {
         const prediction = model.respond("Tell me about The Hobbit.", {
           structured: {
             type: "json",
-            jsonSchema: {
-              type: "object",
-              properties: {
-                title: { type: "string" },
-                author: { type: "string" },
-                year: { type: "integer" },
-              },
-              required: ["title", "author", "year"],
-            },
+            jsonSchema: schema,
           },
         });
 

2_typescript/2_llm-prediction/working-with-chats.md

@@ -3,7 +3,7 @@ title: Working with Chats
 description: APIs for representing a chat conversation with an LLM
 ---
 
-SDK methods such as `llm.respond()`, `llm.applyPromptTemplate()`, or `llm.act()`
+SDK methods such as `model.respond()`, `model.applyPromptTemplate()`, or `model.act()`
 takes in a chat parameter as an input. There are a few ways to represent a chat in the SDK.
 
 ## Option 1: Array of Messages
@@ -15,7 +15,7 @@ variants:
   "Text-only":
     language: typescript
     code: |
-      const prediction = llm.respond([
+      const prediction = model.respond([
         { role: "system", content: "You are a resident AI philosopher." },
         { role: "user", content: "What is the meaning of life?" },
       ]);
@@ -24,7 +24,7 @@ variants:
     code: |
       const image = await client.files.prepareImage("/path/to/image.jpg");
 
-      const prediction = llm.respond([
+      const prediction = model.respond([
         { role: "system", content: "You are a state-of-art object recognition system." },
         { role: "user", content: "What is this object?", images: [image] },
       ]);
@@ -39,7 +39,7 @@ variants:
   TypeScript:
     language: typescript
     code: |
-      const prediction = llm.respond("What is the meaning of life?");
+      const prediction = model.respond("What is the meaning of life?");
 ```
 
 ## Option 3: Using the `Chat` Helper Class
@@ -55,7 +55,7 @@ variants:
       chat.append("system", "You are a resident AI philosopher.");
       chat.append("user", "What is the meaning of life?");
 
-      const prediction = llm.respond(chat);
+      const prediction = model.respond(chat);
   With Images:
     language: typescript
     code: |
@@ -65,7 +65,7 @@ variants:
       chat.append("system", "You are a state-of-art object recognition system.");
       chat.append("user", "What is this object?", { images: [image] });
 
-      const prediction = llm.respond(chat);
+      const prediction = model.respond(chat);
 ```
 
 You can also quickly construct a `Chat` object using the `Chat.from` method.

2_typescript/4_tokenization/index.md

@@ -18,9 +18,9 @@ You can tokenize a string with a loaded LLM or embedding model using the SDK. In
         import { LMStudioClient } from "@lmstudio/sdk";
 
         const client = new LMStudioClient();
-        const llm = await client.llm.model();
+        const model = await client.llm.model();
 
-        const tokens = await llm.tokenize("Hello, world!");
+        const tokens = await model.tokenize("Hello, world!");
 
         console.info(tokens); // Array of token IDs.
 ```
@@ -34,7 +34,7 @@ If you only care about the number of tokens, you can use the `.countTokens` meth
     TypeScript:
       language: typescript
       code: |
-        const tokenCount = await llm.countTokens("Hello, world!");
+        const tokenCount = await model.countTokens("Hello, world!");
         console.info("Token count:", tokenCount);
 ```
 
@@ -72,7 +72,7 @@ You can determine if a given conversation fits into a model's context by doing t
           // ... More messages
         ]);
 
-        console.info("Fits", await doesChatFitInContext(model, chat));
+        console.info("Fits in context:", await doesChatFitInContext(model, chat));
 ```
 
 <!-- ### Context length comparisons

2_typescript/5_manage-models/loading.md

@@ -62,7 +62,9 @@ Use `load()` to load a new instance of a model, even if one already exists. This
         const client = new LMStudioClient();
 
         const llama = await client.llm.load("llama-3.2-1b-instruct");
-        const another_llama = await client.llm.load("llama-3.2-1b-instruct", "second-llama");
+        const another_llama = await client.llm.load("llama-3.2-1b-instruct", {
+          identifier: "second-llama"
+        });
 ```
 
 Learn more about the `.load()` method and the parameters it accepts in the [API Reference](../api-reference/load).
@@ -86,8 +88,8 @@ Once you no longer need a model, you can unload it by simply calling `unload()`
 
         const client = new LMStudioClient();
 
-        const llm = await client.llm.model();
-        await llm.unload()
+        const model = await client.llm.model();
+        await model.unload();
 ```
 
 ## Set Custom Load Config Parameters

2_typescript/6_model-info/get-load-config.md → 2_typescript/6_model-info/_get-load-config.md

@@ -20,7 +20,7 @@ Context length is a special case that [has its own method](/docs/api/sdk/get-con
         import { LMStudioClient } from "@lmstudio/sdk";
 
         const client = new LMStudioClient();
-        const llm = await client.llm.model();
+        const model = await client.llm.model();
 
-        loadConfig = await llm.getLoadConfig()
+        loadConfig = await model.getLoadConfig()
 ```

2_typescript/6_model-info/get-context-length.md

@@ -54,5 +54,5 @@ You can determine if a given conversation fits into a model's context by doing t
           // ... More messages
         ]);
 
-        console.info("Fits", await doesChatFitInContext(model, chat));
+        console.info("Fits in context:", await doesChatFitInContext(model, chat));
 ```

2_typescript/6_model-info/get-model-info.md

@@ -17,7 +17,7 @@ and the `path` used to [load it](/docs/api/sdk/load-model). In the below example
         import { LMStudioClient } from "@lmstudio/sdk";
 
         const client = new LMStudioClient();
-        const llm = await client.llm.model();
+        const model = await client.llm.model();
 
-        model_info = await llm.getInfo()
+        const model_info = await model.getInfo();
 ```