Merge branch 'main' of github.com:run-llama/LlamaIndexTS

apps/docs/docs/end_to_end.md

@@ -18,6 +18,10 @@ Create a list index and query it. This example also use the `LLMRetriever`, whic
 
 Create a vector index and query it. The vector index will use embeddings to fetch the top k most relevant nodes. By default, the top k is 2.
 
+## [Customized Vector Index](https://github.com/run-llama/LlamaIndexTS/blob/main/apps/simple/vectorIndexCustomize.ts)
+
+Create a vector index and query it, while also configuring the the `LLM`, the `ServiceContext`, and the `similarity_top_k`.
+
 ## [OpenAI LLM](https://github.com/run-llama/LlamaIndexTS/blob/main/apps/simple/openai.ts)
 
 Create an OpenAI LLM and directly use it for chat. 

apps/docs/docs/modules/high_level/query_engine.md

@@ -8,7 +8,7 @@ A query engine wraps a `Retriever` and a `ResponseSynthesizer` into a pipeline,
 
 ```typescript
 const queryEngine = index.asQueryEngine();
-const response = queryEngine.query("query string");
+const response = await queryEngine.query("query string");
 ```
 
 ## Sub Question Query Engine

apps/docs/docs/modules/low_level/embedding.md

@@ -9,11 +9,11 @@ The embedding model in LlamaIndex is responsible for creating numerical represen
 This can be explicitly set in the `ServiceContext` object.
 
 ```typescript
-import { OpenAIEmbedding, ServiceContext } from "llamaindex";
+import { OpenAIEmbedding, serviceContextFromDefaults } from "llamaindex";
 
 const openaiEmbeds = new OpenAIEmbedding();
 
-const serviceContext = new ServiceContext({ embedModel: openaiEmbeds });
+const serviceContext = serviceContextFromDefaults({ embedModel: openaiEmbeds });
 ```
 
 ## API Reference

apps/docs/docs/modules/low_level/llm.md

@@ -9,14 +9,14 @@ The LLM is responsible for reading text and generating natural language response
 The LLM can be explicitly set in the `ServiceContext` object.
 
 ```typescript
-import { ChatGPTLLMPredictor, ServiceContext } from "llamaindex";
+import { OpenAI, serviceContextFromDefaults } from "llamaindex";
 
-const openaiLLM = new ChatGPTLLMPredictor({ model: "gpt-3.5-turbo" });
+const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
 
-const serviceContext = new ServiceContext({ llmPredictor: openaiLLM });
+const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
 ```
 
 ## API Reference
 
-- [ChatGPTLLMPredictor](../../api/classes/ChatGPTLLMPredictor.md)
+- [OpenAI](../../api/classes/OpenAI.md)
 - [ServiceContext](../../api/interfaces/ServiceContext.md)
\ No newline at end of file

apps/simple/chatEngine.ts

@@ -26,7 +26,7 @@ async function main() {
   while (true) {
     const query = await rl.question("Query: ");
     const response = await chatEngine.chat(query);
-    console.log(response);
+    console.log(response.toString());
   }
 }
 

apps/simple/openai.ts

-// @ts-ignore
-import process from "node:process";
-import { Configuration, OpenAIWrapper } from "llamaindex/src/llm/openai";
+import { OpenAI } from "llamaindex";
 
 (async () => {
-  const configuration = new Configuration({
-    apiKey: process.env.OPENAI_API_KEY,
-  });
-
-  const openai = new OpenAIWrapper(configuration);
-
-  const { data } = await openai.createChatCompletion({
-    model: "gpt-3.5-turbo-0613",
-    messages: [{ role: "user", content: "Hello, world!" }],
-  });
-
-  console.log(data);
-  console.log(data.choices[0].message);
+  const llm = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.0 });
+  
+  // complete api
+  const response1 = await llm.complete("How are you?");
+  console.log(response1.message.content);
+
+  // chat api
+  const response2 = await llm.chat([{ content: "Tell me a joke!", role: "user" }]);
+  console.log(response2.message.content);
 })();

apps/simple/subquestion.ts

@@ -22,5 +22,5 @@ import essay from "./essay";
     "How was Paul Grahams life different before and after YC?"
   );
 
-  console.log(response);
+  console.log(response.toString());
 })();

apps/simple/vectorIndexCustomize.ts

-import { Document, VectorStoreIndex, RetrieverQueryEngine } from "llamaindex";
+import { Document, VectorStoreIndex, RetrieverQueryEngine, OpenAI, serviceContextFromDefaults } from "llamaindex";
 import essay from "./essay";
 
 // Customize retrieval and query args
 async function main() {
   const document = new Document({ text: essay });
-  const index = await VectorStoreIndex.fromDocuments([document]);
+
+  const serviceContext = serviceContextFromDefaults(
+    { llm: new OpenAI({ model: "gpt-3.5-turbo", temperature: 0.0 }) }
+  );
+
+  const index = await VectorStoreIndex.fromDocuments([document], undefined, serviceContext);
+  
   const retriever = index.asRetriever();
   retriever.similarityTopK = 5;
   // TODO: cannot pass responseSynthesizer into retriever query engine
   const queryEngine = new RetrieverQueryEngine(retriever);
+  
   const response = await queryEngine.query(
     "What did the author do growing up?"
   );