Fix long tokens, split token based on curly brackets

Author: st3w4r

examples/02_colors.js

@@ -33,7 +33,7 @@ async function callGenerateColors(
                     "Give me a palette of 5 gorgeous color with the hex code, name and a description.",
             },
         ],
-        model: "gpt-3.5-turbo", // OR "gpt-4"
+        model: "gpt-4-turbo-preview", // OR "gpt-4"
         stream: true, // ENABLE STREAMING
         temperature: 1.3,
         functions: [

examples/03_colors_raw_json.js

@@ -26,7 +26,7 @@ async function callGenerateColors(
                     "Give me a palette of 5 gorgeous color with the hex code, name and a description.",
             },
         ],
-        model: "gpt-3.5-turbo", // OR "gpt-4"
+        model: "gpt-4-turbo-preview", // OR "gpt-4"
         stream: true, // ENABLE STREAMING
         temperature: 1.3,
         functions: [

examples/05_postcodes.js

@@ -23,7 +23,7 @@ async function main() {
                 content: "Give me 3 cities and their postcodes in California.",
             },
         ],
-        model: "gpt-3.5-turbo", // OR "gpt-4"
+        model: "gpt-3.5-turbo", // OR "gpt-4" OR "gpt-4-turbo-preview"
         stream: true, // ENABLE STREAMING
         temperature: 1.1,
         functions: [
@@ -67,7 +67,7 @@ async function main() {
     // - StreamObjectKeyValue:       (PROGRESSIVE)  Stream of JSON objects and key value pairs
     // - StreamObject:               (ONE-BY-ONE)   Stream of JSON objects
     // - NoStream:                   (ALL-TOGETHER) All the data is returned at the end of the process
-    const mode = StreamMode.StreamObjectKeyValueTokens;
+    const mode = StreamMode.StreamObject;
 
     // Create an instance of the handler
     const openAiHandler = new OpenAiHandler(mode);

package-lock.json

@@ -17,6 +17,7 @@
   "packageManager": "[email protected]",
   "dependencies": {
     "@changesets/cli": "^2.26.2",
+    "openai": "^4.26.0",
     "turbo": "^1.10.14"
   },
   "scripts": {

package.json

@@ -40,7 +40,7 @@
         "typescript": "^5.0.0"
     },
     "dependencies": {
-        "openai": "^4.6.0",
+        "openai": "^4.26.0",
         "zod": "^3.22.3",
         "zod-to-json-schema": "^3.21.4"
     },

packages/openai-partial-stream/package.json

@@ -29,17 +29,23 @@ export class OpenAiHandler {
                 continue;
             }
 
-            const res = this.parser.parse(content);
-
-            if (
-                this.mode === StreamMode.NoStream ||
-                this.mode === StreamMode.Batch
-            ) {
-                if (res) {
-                    this.noStreamBufferList.push(res);
+            // TODO: Handle this in the stream parser
+            // The stream parser should be able to return multi responses.
+            const chunks = content.split(/(?<={|})/);
+
+            for (const chunk of chunks) {
+                const res = this.parser.parse(chunk);
+
+                if (
+                    this.mode === StreamMode.NoStream ||
+                    this.mode === StreamMode.Batch
+                ) {
+                    if (res) {
+                        this.noStreamBufferList.push(res);
+                    }
+                } else if (res) {
+                    yield res;
                 }
-            } else if (res) {
-                yield res;
             }
         }
 

packages/openai-partial-stream/src/openAiHandler.ts

@@ -217,3 +217,57 @@ test("stream partial", async () => {
 
     expect(results).toEqual(expected);
 });
+
+// TODO: Improve the parer to handle this case
+// Parser should be able to return an array when their is mutli object closed
+// In the same chunk
+test.skip("stream partial longer tokens", async () => {
+    const inputs = [
+        `{ "colors": [{"hex": "#FF7F50`,
+        `"},{`,
+        `"he`,
+        `x": "#465`,
+        `2B4"}] }`,
+    ];
+
+    // TODO: Add another case
+    // const inputs = [
+    //     `
+    //     { "colors": [{"a":1},{"b":2},{"c":3`,
+    //     `}`,
+    //     `] }`,
+    // ];
+
+    const streamParser = new StreamParser(StreamMode.StreamObject);
+
+    const results = inputs.map((item) => streamParser.parse(item));
+
+    const expected = [
+        null,
+        [
+            {
+                index: 0,
+                status: "COMPLETED",
+                data: { colors: [{ hex: "#FF7F50" }] },
+            },
+            {
+                index: 1,
+                status: "PARTIAL",
+                data: { colors: [{ hex: "#FF7F50" }, {}] },
+            },
+        ],
+        null,
+        null,
+        {
+            index: 1,
+            status: "COMPLETED",
+            data: { colors: [{ hex: "#FF7F50" }, { hex: "#4652B4" }] },
+        },
+    ];
+
+    results.forEach((result) => {
+        console.log(result?.index, result?.status, result?.data);
+    });
+
+    expect(results).toEqual(expected);
+});