diff --git a/apps/docs/docs/end_to_end.md b/apps/docs/docs/end_to_end.md
index d30ad16756edb5a9c3d30b870184e43cf1dd8dc5..1b4ca433804742e90d5b8239fea8ac462ac1263b 100644
--- a/apps/docs/docs/end_to_end.md
+++ b/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.
diff --git a/apps/docs/docs/modules/high_level/query_engine.md b/apps/docs/docs/modules/high_level/query_engine.md
index 20dbe35b2063163d3cbcbd8e693d5653051cf287..c6d6452a199bb73801928ad4bf82879bbd9c020e 100644
--- a/apps/docs/docs/modules/high_level/query_engine.md
+++ b/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
diff --git a/apps/docs/docs/modules/low_level/embedding.md b/apps/docs/docs/modules/low_level/embedding.md
index 645f33459cc5ac0a8487f428d60ea89396dacb7e..57f672abef2a36cb3bdf49037a5f4f1b76d9d5f7 100644
--- a/apps/docs/docs/modules/low_level/embedding.md
+++ b/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
diff --git a/apps/docs/docs/modules/low_level/llm.md b/apps/docs/docs/modules/low_level/llm.md
index 29e8a8879104cff9a7bd57d4429dcfd59175f6dd..4f0ba2db5a49e523b317b9aea7d010381309d930 100644
--- a/apps/docs/docs/modules/low_level/llm.md
+++ b/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
diff --git a/apps/simple/chatEngine.ts b/apps/simple/chatEngine.ts
index 97485b49701bf67ec9a1d96fbc6e02a5da340500..a79bfd88c6065e09b87586da0a13020b4c93709b 100644
--- a/apps/simple/chatEngine.ts
+++ b/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());
}
}
diff --git a/apps/simple/openai.ts b/apps/simple/openai.ts
index 12e91f67a8f4461aa5fb68b6185642ebdff6066d..f53709c6495d2a098a439e97b1a1f54321ec6ca3 100644
--- a/apps/simple/openai.ts
+++ b/apps/simple/openai.ts
@@ -1,19 +1,13 @@
-// @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);
})();
diff --git a/apps/simple/subquestion.ts b/apps/simple/subquestion.ts
index e386a296c8d2b6cffc23554dfbe799f3f2e337b8..ff7c8225f96823f93c5908c5a6bdad5b67d3281e 100644
--- a/apps/simple/subquestion.ts
+++ b/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());
})();
diff --git a/apps/simple/vectorIndexCustomize.ts b/apps/simple/vectorIndexCustomize.ts
index 49d5ca4d80be166291502b58f65d2090410ab775..aa7ebc6ae0a0000d46f1686d8052ed2926d423e2 100644
--- a/apps/simple/vectorIndexCustomize.ts
+++ b/apps/simple/vectorIndexCustomize.ts
@@ -1,14 +1,21 @@
-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?"
);