fix: interrupt

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

.changeset/afraid-seahorses-develop.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/workflow": patch
+---
+
+fix: output event check

.changeset/cool-cows-wonder.md

@@ -0,0 +1,5 @@
+---
+"@llamaindex/workflow": patch
+---
+
+feat: recoverable context with error handling

apps/docs/CHANGELOG.md

@@ -1,5 +1,33 @@
 # docs
 
+## 0.0.116
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
+## 0.0.115
+
+### Patch Changes
+
+- llamaindex@0.8.11
+
+## 0.0.114
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+  - @llamaindex/examples@0.0.14
+
+## 0.0.113
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+
 ## 0.0.112
 
 ### Patch Changes

apps/docs/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docs",
-  "version": "0.0.112",
+  "version": "0.0.116",
   "private": true,
   "scripts": {
     "docusaurus": "docusaurus",

apps/next/CHANGELOG.md

@@ -1,5 +1,58 @@
 # @llamaindex/doc
 
+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+  - @llamaindex/cloud@2.0.9
+  - llamaindex@0.8.12
+  - @llamaindex/node-parser@0.0.10
+  - @llamaindex/readers@1.0.10
+
+## 0.0.13
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+  - @llamaindex/cloud@2.0.8
+  - llamaindex@0.8.11
+  - @llamaindex/node-parser@0.0.9
+  - @llamaindex/openai@0.1.33
+  - @llamaindex/readers@1.0.9
+
+## 0.0.12
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+- Updated dependencies [fd8c882]
+  - llamaindex@0.8.10
+  - @llamaindex/core@0.4.7
+  - @llamaindex/workflow@0.0.4
+  - @llamaindex/cloud@2.0.7
+  - @llamaindex/node-parser@0.0.8
+  - @llamaindex/openai@0.1.32
+  - @llamaindex/readers@1.0.8
+
+## 0.0.11
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+  - @llamaindex/cloud@2.0.6
+  - @llamaindex/core@0.4.6
+  - @llamaindex/node-parser@0.0.7
+  - @llamaindex/openai@0.1.31
+  - @llamaindex/readers@1.0.7
+
 ## 0.0.10
 
 ### Patch Changes

apps/next/next.config.mjs

@@ -6,6 +6,16 @@ const withMDX = createMDX();
 const config = {
   reactStrictMode: true,
   transpilePackages: ["monaco-editor"],
+  images: {
+    remotePatterns: [
+      {
+        protocol: "https",
+        hostname: "mermaid.ink",
+        port: "",
+        pathname: "/**",
+      },
+    ],
+  },
   webpack: (config, { isServer }) => {
     if (Array.isArray(config.target) && config.target.includes("web")) {
       config.target = ["web", "es2020"];

apps/next/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/doc",
-  "version": "0.0.10",
+  "version": "0.0.14",
   "private": true,
   "scripts": {
     "build": "pnpm run build:docs && next build",
@@ -24,6 +24,8 @@
     "@radix-ui/react-dialog": "^1.1.2",
     "@radix-ui/react-icons": "^1.3.1",
     "@radix-ui/react-label": "^2.1.0",
+    "@radix-ui/react-select": "^2.1.2",
+    "@radix-ui/react-separator": "^1.1.0",
     "@radix-ui/react-slider": "^1.2.1",
     "@radix-ui/react-slot": "^1.1.0",
     "@radix-ui/react-tooltip": "^1.1.3",
@@ -52,6 +54,7 @@
     "react-text-transition": "^3.1.0",
     "react-use-measure": "^2.1.1",
     "rehype-katex": "^7.0.1",
+    "rehype-mermaid": "^3.0.0",
     "remark-math": "^6.0.0",
     "rimraf": "^6.0.1",
     "shiki": "^1.22.2",

apps/next/src/components/demo/checkout.tsx

@@ -0,0 +1,213 @@
+"use client";
+import type { ShippingInfo } from "@/components/demo/checkout/shpping";
+import {
+  StartEvent,
+  StopEvent,
+  Workflow,
+  WorkflowContext,
+  WorkflowEvent,
+} from "@llamaindex/workflow";
+import { ReactNode, useCallback, useState } from "react";
+import { Button } from "../ui/button";
+import {
+  Card,
+  CardContent,
+  CardFooter,
+  CardHeader,
+  CardTitle,
+} from "../ui/card";
+import { Separator } from "../ui/separator";
+
+type Context = {
+  userId: string;
+  items: { name: string; price: number; quantity: number }[];
+
+  // utility functions with frontend
+  update: (ui: ReactNode) => void;
+  interrupt: () => void;
+};
+
+type UserInfo = {
+  id: string;
+  name: string;
+  email: string;
+  shippingAddress: ShippingInfo;
+};
+
+const getUser = async (userId: string): Promise<UserInfo | null> => {
+  await new Promise((resolve) => setTimeout(resolve, 1000));
+  const user = localStorage.getItem(`workflow-demo-user:${userId}`);
+  if (user !== null) {
+    return JSON.parse(user) as UserInfo;
+  } else {
+    return null;
+  }
+};
+
+const checkoutWorkflow = new Workflow<Context, void, void>({});
+
+// 1. User click checkout button
+// 2. Check if user has correct information
+//   - If not, show shipping information form
+// 3. Proceed to payment
+// 4. Confirm the order
+// 5. Send confirmation email
+
+class ShowShippingInformationFormEvent extends WorkflowEvent<void> {}
+
+class ProceedToPaymentEvent extends WorkflowEvent<void> {}
+
+class ConfirmOrderEvent extends WorkflowEvent<void> {}
+
+class SendConfirmationEmailEvent extends WorkflowEvent<void> {}
+
+checkoutWorkflow.addStep(
+  {
+    inputs: [StartEvent],
+    outputs: [ProceedToPaymentEvent, ShowShippingInformationFormEvent],
+  },
+  async ({ data }, _) => {
+    const user = await getUser(data.userId);
+    if (user === null) {
+      return new ShowShippingInformationFormEvent();
+    }
+    // todo
+    return new ProceedToPaymentEvent();
+  },
+);
+
+checkoutWorkflow.addStep(
+  {
+    inputs: [ShowShippingInformationFormEvent],
+    outputs: [ProceedToPaymentEvent],
+  },
+  async ({ data }) => {
+    const user = await getUser(data.userId);
+    if (user === null) {
+      data.update("TODO");
+      data.interrupt();
+    }
+    return new ProceedToPaymentEvent();
+  },
+);
+
+checkoutWorkflow.addStep(
+  {
+    inputs: [ProceedToPaymentEvent],
+    outputs: [ConfirmOrderEvent],
+  },
+  async () => {
+    return new ConfirmOrderEvent();
+  },
+);
+
+checkoutWorkflow.addStep(
+  {
+    inputs: [ConfirmOrderEvent],
+    outputs: [SendConfirmationEmailEvent],
+  },
+  async () => {
+    return new SendConfirmationEmailEvent();
+  },
+);
+
+checkoutWorkflow.addStep(
+  {
+    inputs: [SendConfirmationEmailEvent],
+    outputs: [StopEvent<void>],
+  },
+  async () => {
+    return new StopEvent(void 0);
+  },
+);
+
+async function runContext(context: WorkflowContext<void, void, Context>) {
+  try {
+    await context;
+  } catch (e) {
+    if (e instanceof Error && e.message === "Interrupted") {
+      const snapshot = context.snapshot();
+      // for each step, save the snapshot into the local storage
+      localStorage.setItem(
+        "workflow-snapshot",
+        new TextDecoder().decode(snapshot),
+      );
+    } else {
+      throw e;
+    }
+  }
+}
+
+export const CheckoutDemo = () => {
+  const items = [
+    { name: "T-Shirt", price: 19.99, quantity: 2 },
+    { name: "Jeans", price: 49.99, quantity: 1 },
+    { name: "Sneakers", price: 79.99, quantity: 1 },
+  ];
+
+  const [ui, setUI] = useState<ReactNode>(null);
+
+  const [contextData, setContextData] = useState<Context>({
+    userId: "1",
+    items: items,
+    update: (ui) => setUI(ui),
+    interrupt: () => {
+      throw new Error("Interrupted");
+    },
+  });
+
+  const subtotal = items.reduce(
+    (acc, item) => acc + item.price * item.quantity,
+    0,
+  );
+  const tax = subtotal * 0.1; // Assuming 10% tax
+  const total = subtotal + tax;
+
+  const onClickStartCheckout = useCallback(() => {
+    const context = checkoutWorkflow.run().with(contextData);
+    runContext(context);
+  }, []);
+
+  return (
+    <div>
+      {ui}
+      <Card className="w-full max-w-md mx-auto">
+        <CardHeader>
+          <CardTitle>Your Order</CardTitle>
+        </CardHeader>
+        <CardContent>
+          <ul className="space-y-2">
+            {items.map((item, index) => (
+              <li key={index} className="flex justify-between items-center">
+                <span>
+                  {item.name} x{item.quantity}
+                </span>
+                <span>${(item.price * item.quantity).toFixed(2)}</span>
+              </li>
+            ))}
+          </ul>
+          <Separator className="my-4" />
+          <div className="space-y-2">
+            <div className="flex justify-between">
+              <span>Subtotal</span>
+              <span>${subtotal.toFixed(2)}</span>
+            </div>
+            <div className="flex justify-between">
+              <span>Tax</span>
+              <span>${tax.toFixed(2)}</span>
+            </div>
+            <div className="flex justify-between font-bold">
+              <span>Total</span>
+              <span>${total.toFixed(2)}</span>
+            </div>
+          </div>
+        </CardContent>
+        <CardFooter>
+          <Button className="w-full" onClick={onClickStartCheckout}>
+            Proceed to Checkout
+          </Button>
+        </CardFooter>
+      </Card>
+    </div>
+  );
+};

apps/next/src/components/demo/checkout/shpping.tsx

@@ -0,0 +1,126 @@
+"use client";
+import { Button } from "@/components/ui/button";
+import { Input } from "@/components/ui/input";
+import { Label } from "@/components/ui/label";
+import {
+  Select,
+  SelectContent,
+  SelectItem,
+  SelectTrigger,
+  SelectValue,
+} from "@/components/ui/select";
+import { useState } from "react";
+
+export function ShippingForm({
+  onSubmit,
+}: {
+  onSubmit: (data: ShippingInfo) => void;
+}) {
+  const [formData, setFormData] = useState<ShippingInfo>({
+    fullName: "",
+    address: "",
+    city: "",
+    state: "",
+    zipCode: "",
+    country: "",
+  });
+
+  const handleChange = (e: React.ChangeEvent<HTMLInputElement>) => {
+    const { name, value } = e.target;
+    setFormData((prev) => ({ ...prev, [name]: value }));
+  };
+
+  const handleCountryChange = (value: string) => {
+    setFormData((prev) => ({ ...prev, country: value }));
+  };
+
+  const handleSubmit = (e: React.FormEvent) => {
+    e.preventDefault();
+    onSubmit(formData);
+  };
+
+  return (
+    <form onSubmit={handleSubmit} className="space-y-4">
+      <div>
+        <Label htmlFor="fullName">Full Name</Label>
+        <Input
+          id="fullName"
+          name="fullName"
+          value={formData.fullName}
+          onChange={handleChange}
+          required
+        />
+      </div>
+      <div>
+        <Label htmlFor="address">Address</Label>
+        <Input
+          id="address"
+          name="address"
+          value={formData.address}
+          onChange={handleChange}
+          required
+        />
+      </div>
+      <div className="grid grid-cols-2 gap-4">
+        <div>
+          <Label htmlFor="city">City</Label>
+          <Input
+            id="city"
+            name="city"
+            value={formData.city}
+            onChange={handleChange}
+            required
+          />
+        </div>
+        <div>
+          <Label htmlFor="state">State</Label>
+          <Input
+            id="state"
+            name="state"
+            value={formData.state}
+            onChange={handleChange}
+            required
+          />
+        </div>
+      </div>
+      <div className="grid grid-cols-2 gap-4">
+        <div>
+          <Label htmlFor="zipCode">ZIP Code</Label>
+          <Input
+            id="zipCode"
+            name="zipCode"
+            value={formData.zipCode}
+            onChange={handleChange}
+            required
+          />
+        </div>
+        <div>
+          <Label htmlFor="country">Country</Label>
+          <Select onValueChange={handleCountryChange} value={formData.country}>
+            <SelectTrigger id="country">
+              <SelectValue placeholder="Select country" />
+            </SelectTrigger>
+            <SelectContent>
+              <SelectItem value="us">United States</SelectItem>
+              <SelectItem value="ca">Canada</SelectItem>
+              <SelectItem value="uk">United Kingdom</SelectItem>
+              {/* Add more countries as needed */}
+            </SelectContent>
+          </Select>
+        </div>
+      </div>
+      <Button type="submit" className="w-full">
+        Save Shipping Information
+      </Button>
+    </form>
+  );
+}
+
+export interface ShippingInfo {
+  fullName: string;
+  address: string;
+  city: string;
+  state: string;
+  zipCode: string;
+  country: string;
+}

apps/next/src/components/ui/card.tsx

@@ -0,0 +1,83 @@
+import * as React from "react";
+
+import { cn } from "@/lib/utils";
+
+const Card = React.forwardRef<
+  HTMLDivElement,
+  React.HTMLAttributes<HTMLDivElement>
+>(({ className, ...props }, ref) => (
+  <div
+    ref={ref}
+    className={cn(
+      "rounded-xl border bg-card text-card-foreground shadow",
+      className,
+    )}
+    {...props}
+  />
+));
+Card.displayName = "Card";
+
+const CardHeader = React.forwardRef<
+  HTMLDivElement,
+  React.HTMLAttributes<HTMLDivElement>
+>(({ className, ...props }, ref) => (
+  <div
+    ref={ref}
+    className={cn("flex flex-col space-y-1.5 p-6", className)}
+    {...props}
+  />
+));
+CardHeader.displayName = "CardHeader";
+
+const CardTitle = React.forwardRef<
+  HTMLDivElement,
+  React.HTMLAttributes<HTMLDivElement>
+>(({ className, ...props }, ref) => (
+  <div
+    ref={ref}
+    className={cn("font-semibold leading-none tracking-tight", className)}
+    {...props}
+  />
+));
+CardTitle.displayName = "CardTitle";
+
+const CardDescription = React.forwardRef<
+  HTMLDivElement,
+  React.HTMLAttributes<HTMLDivElement>
+>(({ className, ...props }, ref) => (
+  <div
+    ref={ref}
+    className={cn("text-sm text-muted-foreground", className)}
+    {...props}
+  />
+));
+CardDescription.displayName = "CardDescription";
+
+const CardContent = React.forwardRef<
+  HTMLDivElement,
+  React.HTMLAttributes<HTMLDivElement>
+>(({ className, ...props }, ref) => (
+  <div ref={ref} className={cn("p-6 pt-0", className)} {...props} />
+));
+CardContent.displayName = "CardContent";
+
+const CardFooter = React.forwardRef<
+  HTMLDivElement,
+  React.HTMLAttributes<HTMLDivElement>
+>(({ className, ...props }, ref) => (
+  <div
+    ref={ref}
+    className={cn("flex items-center p-6 pt-0", className)}
+    {...props}
+  />
+));
+CardFooter.displayName = "CardFooter";
+
+export {
+  Card,
+  CardContent,
+  CardDescription,
+  CardFooter,
+  CardHeader,
+  CardTitle,
+};

apps/next/src/components/ui/select.tsx

@@ -0,0 +1,162 @@
+"use client";
+
+import { cn } from "@/lib/utils";
+import {
+  CheckIcon,
+  ChevronDownIcon,
+  ChevronUpIcon,
+} from "@radix-ui/react-icons";
+import * as SelectPrimitive from "@radix-ui/react-select";
+import * as React from "react";
+
+const Select = SelectPrimitive.Root;
+
+const SelectGroup = SelectPrimitive.Group;
+
+const SelectValue = SelectPrimitive.Value;
+
+const SelectTrigger = React.forwardRef<
+  React.ElementRef<typeof SelectPrimitive.Trigger>,
+  React.ComponentPropsWithoutRef<typeof SelectPrimitive.Trigger>
+>(({ className, children, ...props }, ref) => (
+  <SelectPrimitive.Trigger
+    ref={ref}
+    className={cn(
+      "flex h-9 w-full items-center justify-between whitespace-nowrap rounded-md border border-input bg-transparent px-3 py-2 text-sm shadow-sm ring-offset-background placeholder:text-muted-foreground focus:outline-none focus:ring-1 focus:ring-ring disabled:cursor-not-allowed disabled:opacity-50 [&>span]:line-clamp-1",
+      className,
+    )}
+    {...props}
+  >
+    {children}
+    <SelectPrimitive.Icon asChild>
+      <ChevronDownIcon className="h-4 w-4 opacity-50" />
+    </SelectPrimitive.Icon>
+  </SelectPrimitive.Trigger>
+));
+SelectTrigger.displayName = SelectPrimitive.Trigger.displayName;
+
+const SelectScrollUpButton = React.forwardRef<
+  React.ElementRef<typeof SelectPrimitive.ScrollUpButton>,
+  React.ComponentPropsWithoutRef<typeof SelectPrimitive.ScrollUpButton>
+>(({ className, ...props }, ref) => (
+  <SelectPrimitive.ScrollUpButton
+    ref={ref}
+    className={cn(
+      "flex cursor-default items-center justify-center py-1",
+      className,
+    )}
+    {...props}
+  >
+    <ChevronUpIcon className="h-4 w-4" />
+  </SelectPrimitive.ScrollUpButton>
+));
+SelectScrollUpButton.displayName = SelectPrimitive.ScrollUpButton.displayName;
+
+const SelectScrollDownButton = React.forwardRef<
+  React.ElementRef<typeof SelectPrimitive.ScrollDownButton>,
+  React.ComponentPropsWithoutRef<typeof SelectPrimitive.ScrollDownButton>
+>(({ className, ...props }, ref) => (
+  <SelectPrimitive.ScrollDownButton
+    ref={ref}
+    className={cn(
+      "flex cursor-default items-center justify-center py-1",
+      className,
+    )}
+    {...props}
+  >
+    <ChevronDownIcon className="h-4 w-4" />
+  </SelectPrimitive.ScrollDownButton>
+));
+SelectScrollDownButton.displayName =
+  SelectPrimitive.ScrollDownButton.displayName;
+
+const SelectContent = React.forwardRef<
+  React.ElementRef<typeof SelectPrimitive.Content>,
+  React.ComponentPropsWithoutRef<typeof SelectPrimitive.Content>
+>(({ className, children, position = "popper", ...props }, ref) => (
+  <SelectPrimitive.Portal>
+    <SelectPrimitive.Content
+      ref={ref}
+      className={cn(
+        "relative z-50 max-h-96 min-w-[8rem] overflow-hidden rounded-md border bg-popover text-popover-foreground shadow-md data-[state=open]:animate-in data-[state=closed]:animate-out data-[state=closed]:fade-out-0 data-[state=open]:fade-in-0 data-[state=closed]:zoom-out-95 data-[state=open]:zoom-in-95 data-[side=bottom]:slide-in-from-top-2 data-[side=left]:slide-in-from-right-2 data-[side=right]:slide-in-from-left-2 data-[side=top]:slide-in-from-bottom-2",
+        position === "popper" &&
+          "data-[side=bottom]:translate-y-1 data-[side=left]:-translate-x-1 data-[side=right]:translate-x-1 data-[side=top]:-translate-y-1",
+        className,
+      )}
+      position={position}
+      {...props}
+    >
+      <SelectScrollUpButton />
+      <SelectPrimitive.Viewport
+        className={cn(
+          "p-1",
+          position === "popper" &&
+            "h-[var(--radix-select-trigger-height)] w-full min-w-[var(--radix-select-trigger-width)]",
+        )}
+      >
+        {children}
+      </SelectPrimitive.Viewport>
+      <SelectScrollDownButton />
+    </SelectPrimitive.Content>
+  </SelectPrimitive.Portal>
+));
+SelectContent.displayName = SelectPrimitive.Content.displayName;
+
+const SelectLabel = React.forwardRef<
+  React.ElementRef<typeof SelectPrimitive.Label>,
+  React.ComponentPropsWithoutRef<typeof SelectPrimitive.Label>
+>(({ className, ...props }, ref) => (
+  <SelectPrimitive.Label
+    ref={ref}
+    className={cn("px-2 py-1.5 text-sm font-semibold", className)}
+    {...props}
+  />
+));
+SelectLabel.displayName = SelectPrimitive.Label.displayName;
+
+const SelectItem = React.forwardRef<
+  React.ElementRef<typeof SelectPrimitive.Item>,
+  React.ComponentPropsWithoutRef<typeof SelectPrimitive.Item>
+>(({ className, children, ...props }, ref) => (
+  <SelectPrimitive.Item
+    ref={ref}
+    className={cn(
+      "relative flex w-full cursor-default select-none items-center rounded-sm py-1.5 pl-2 pr-8 text-sm outline-none focus:bg-accent focus:text-accent-foreground data-[disabled]:pointer-events-none data-[disabled]:opacity-50",
+      className,
+    )}
+    {...props}
+  >
+    <span className="absolute right-2 flex h-3.5 w-3.5 items-center justify-center">
+      <SelectPrimitive.ItemIndicator>
+        <CheckIcon className="h-4 w-4" />
+      </SelectPrimitive.ItemIndicator>
+    </span>
+    <SelectPrimitive.ItemText>{children}</SelectPrimitive.ItemText>
+  </SelectPrimitive.Item>
+));
+SelectItem.displayName = SelectPrimitive.Item.displayName;
+
+const SelectSeparator = React.forwardRef<
+  React.ElementRef<typeof SelectPrimitive.Separator>,
+  React.ComponentPropsWithoutRef<typeof SelectPrimitive.Separator>
+>(({ className, ...props }, ref) => (
+  <SelectPrimitive.Separator
+    ref={ref}
+    className={cn("-mx-1 my-1 h-px bg-muted", className)}
+    {...props}
+  />
+));
+SelectSeparator.displayName = SelectPrimitive.Separator.displayName;
+
+export {
+  Select,
+  SelectContent,
+  SelectGroup,
+  SelectItem,
+  SelectLabel,
+  SelectScrollDownButton,
+  SelectScrollUpButton,
+  SelectSeparator,
+  SelectTrigger,
+  SelectValue,
+};

apps/next/src/components/ui/separator.tsx

@@ -0,0 +1,31 @@
+"use client";
+
+import * as SeparatorPrimitive from "@radix-ui/react-separator";
+import * as React from "react";
+
+import { cn } from "@/lib/utils";
+
+const Separator = React.forwardRef<
+  React.ElementRef<typeof SeparatorPrimitive.Root>,
+  React.ComponentPropsWithoutRef<typeof SeparatorPrimitive.Root>
+>(
+  (
+    { className, orientation = "horizontal", decorative = true, ...props },
+    ref,
+  ) => (
+    <SeparatorPrimitive.Root
+      ref={ref}
+      decorative={decorative}
+      orientation={orientation}
+      className={cn(
+        "shrink-0 bg-border",
+        orientation === "horizontal" ? "h-[1px] w-full" : "h-full w-[1px]",
+        className,
+      )}
+      {...props}
+    />
+  ),
+);
+Separator.displayName = SeparatorPrimitive.Root.displayName;
+
+export { Separator };

apps/next/src/content/docs/llamaindex/guide/workflow/handler.mdx

@@ -0,0 +1,19 @@
+---
+title: Event Step Handler
+description: Learn how to design a good event handler for your workflow.
+---
+import { CheckoutDemo } from '../../../../../components/demo/checkout'
+
+Let's start an checkout workflow.
+
+<div className='grid grid-cols-2 gap-4'>
+  <CheckoutDemo/>
+  <div
+    className='border p-4'
+    style={{
+      borderColor: 'hsl(var(--border))'
+    }}
+  >
+    [![](https://mermaid.ink/img/pako:eNptkd9ugyAUxl-FcN2-gEu2zD9t7dKtmcuSDXtB5KikCgaPWxrruw_RtmkyruB8Pz7O4etppgVQjxaGNyX5CB9SRex6ZglygyQoITvqDg9kuXwkPvuU8EsCqxwmznf1gEUKwZCklE0jVUFilWtTc5RazWDgwJAlUEGGN3IHWGoxQ6GDotltz081KPzHLHLcir3Dz9jPmxFgZmnlpHUft1OZBNoY--LTMOnrUT9_QXsmG7aveAZ31yf5VZ-JPxU2zi9mFzOVy_teYgds7WBK3OkkqrmsZmrrqBc7mbj9aarogtZgeSlsBP2IphRLqCGlnt0Kbo4pTdVgOd6hTk4qox6aDhbU6K4oqZfzqrWnrhEcIZTc5lhfkIarb62vRxAStdlNebvYhz_ob6Ka?type=png)](https://mermaid.live/edit#pako:eNptkd9ugyAUxl-FcN2-gEu2zD9t7dKtmcuSDXtB5KikCgaPWxrruw_RtmkyruB8Pz7O4etppgVQjxaGNyX5CB9SRex6ZglygyQoITvqDg9kuXwkPvuU8EsCqxwmznf1gEUKwZCklE0jVUFilWtTc5RazWDgwJAlUEGGN3IHWGoxQ6GDotltz081KPzHLHLcir3Dz9jPmxFgZmnlpHUft1OZBNoY--LTMOnrUT9_QXsmG7aveAZ31yf5VZ-JPxU2zi9mFzOVy_teYgds7WBK3OkkqrmsZmrrqBc7mbj9aarogtZgeSlsBP2IphRLqCGlnt0Kbo4pTdVgOd6hTk4qox6aDhbU6K4oqZfzqrWnrhEcIZTc5lhfkIarb62vRxAStdlNebvYhz_ob6Ka)
+  </div>
+</div>

apps/next/src/content/docs/llamaindex/guide/workflow/meta.json

@@ -2,5 +2,12 @@
   "title": "Workflow",
   "description": "See how to use @llamaindex/workflow",
   "defaultOpen": false,
-  "pages": ["index", "different-inputs-outputs", "streaming"]
+  "pages": [
+    "index",
+    "different-inputs-outputs",
+    "streaming",
+    "---Advanced concept---",
+    "handler",
+    "..."
+  ]
 }

apps/next/turbo.json

@@ -1,6 +1,14 @@
 {
   "extends": ["//"],
   "tasks": {
+    "build": {
+      "outputs": [
+        ".next",
+        ".source",
+        "next-env.d.ts",
+        "src/content/docs/cloud/api/**"
+      ]
+    },
     "dev": {
       "dependsOn": ["^build"]
     }

e2e/examples/cloudflare-worker-agent/CHANGELOG.md

@@ -1,5 +1,32 @@
 # @llamaindex/cloudflare-worker-agent-test
 
+## 0.0.108
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
+## 0.0.107
+
+### Patch Changes
+
+- llamaindex@0.8.11
+
+## 0.0.106
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+
+## 0.0.105
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+
 ## 0.0.104
 
 ### Patch Changes

e2e/examples/cloudflare-worker-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloudflare-worker-agent-test",
-  "version": "0.0.104",
+  "version": "0.0.108",
   "type": "module",
   "private": true,
   "scripts": {

e2e/examples/llama-parse-browser/CHANGELOG.md

@@ -1,5 +1,29 @@
 # @llamaindex/llama-parse-browser-test
 
+## 0.0.29
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.9
+
+## 0.0.28
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.8
+
+## 0.0.27
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.7
+
+## 0.0.26
+
+### Patch Changes
+
+- @llamaindex/cloud@2.0.6
+
 ## 0.0.25
 
 ### Patch Changes

e2e/examples/llama-parse-browser/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/llama-parse-browser-test",
   "private": true,
-  "version": "0.0.25",
+  "version": "0.0.29",
   "type": "module",
   "scripts": {
     "dev": "vite",

e2e/examples/nextjs-agent/CHANGELOG.md

@@ -1,5 +1,32 @@
 # @llamaindex/next-agent-test
 
+## 0.1.108
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
+## 0.1.107
+
+### Patch Changes
+
+- llamaindex@0.8.11
+
+## 0.1.106
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+
+## 0.1.105
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+
 ## 0.1.104
 
 ### Patch Changes

e2e/examples/nextjs-agent/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-agent-test",
-  "version": "0.1.104",
+  "version": "0.1.108",
   "private": true,
   "scripts": {
     "dev": "next dev",

e2e/examples/nextjs-edge-runtime/CHANGELOG.md

@@ -1,5 +1,32 @@
 # test-edge-runtime
 
+## 0.1.107
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
+## 0.1.106
+
+### Patch Changes
+
+- llamaindex@0.8.11
+
+## 0.1.105
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+
+## 0.1.104
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+
 ## 0.1.103
 
 ### Patch Changes

e2e/examples/nextjs-edge-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/nextjs-edge-runtime-test",
-  "version": "0.1.103",
+  "version": "0.1.107",
   "private": true,
   "scripts": {
     "dev": "next dev",

e2e/examples/nextjs-node-runtime/CHANGELOG.md

@@ -1,5 +1,32 @@
 # @llamaindex/next-node-runtime
 
+## 0.0.89
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
+## 0.0.88
+
+### Patch Changes
+
+- llamaindex@0.8.11
+
+## 0.0.87
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+
+## 0.0.86
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+
 ## 0.0.85
 
 ### Patch Changes

e2e/examples/nextjs-node-runtime/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/next-node-runtime-test",
-  "version": "0.0.85",
+  "version": "0.0.89",
   "private": true,
   "scripts": {
     "dev": "next dev",

e2e/examples/nextjs-node-runtime/src/actions/openai.ts

@@ -15,7 +15,6 @@ Settings.llm = new OpenAI({
 });
 Settings.embedModel = new HuggingFaceEmbedding({
   modelType: "BAAI/bge-small-en-v1.5",
-  quantized: false,
 });
 Settings.callbackManager.on("llm-tool-call", (event) => {
   console.log(event.detail);

e2e/examples/waku-query-engine/CHANGELOG.md

@@ -1,5 +1,32 @@
 # @llamaindex/waku-query-engine-test
 
+## 0.0.108
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
+## 0.0.107
+
+### Patch Changes
+
+- llamaindex@0.8.11
+
+## 0.0.106
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+
+## 0.0.105
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+
 ## 0.0.104
 
 ### Patch Changes

e2e/examples/waku-query-engine/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/waku-query-engine-test",
-  "version": "0.0.104",
+  "version": "0.0.108",
   "type": "module",
   "private": true,
   "scripts": {

e2e/fixtures/llm/ollama.ts

@@ -0,0 +1,3 @@
+import { OpenAI } from "./openai.js";
+
+export class Ollama extends OpenAI {}

e2e/mock-module.js

@@ -15,7 +15,17 @@ export async function resolve(specifier, context, nextResolve) {
   const targetUrl = fileURLToPath(result.url).replace(/\.js$/, ".ts");
   let relativePath = relative(packageDistDir, targetUrl);
   // todo: make it more generic if we have more sub modules fixtures in the future
-  if (relativePath.startsWith("../../llm/openai")) {
+  if (relativePath.startsWith("../../llm/anthropic")) {
+    relativePath = relativePath.replace(
+      "../../llm/ollama/dist/index.ts",
+      "llm/anthropic.ts",
+    );
+  } else if (relativePath.startsWith("../../llm/ollama")) {
+    relativePath = relativePath.replace(
+      "../../llm/ollama/dist/index.ts",
+      "llm/ollama.ts",
+    );
+  } else if (relativePath.startsWith("../../llm/openai")) {
     relativePath = relativePath.replace(
       "../../llm/openai/dist/index.ts",
       "llm/openai.ts",

e2e/node/embedding/clip.e2e.ts

@@ -64,7 +64,7 @@ await test("clip embedding", async (t) => {
   });
 
   await t.test("custom transformer", async () => {
-    const transformers = await import("@xenova/transformers");
+    const transformers = await import("@huggingface/transformers");
     const getter = test.mock.fn((t, k, r) => {
       return Reflect.get(t, k, r);
     });

e2e/node/ollama.e2e.ts

@@ -0,0 +1,35 @@
+import { Ollama } from "@llamaindex/ollama";
+import assert from "node:assert";
+import { test } from "node:test";
+import { getWeatherTool } from "./fixtures/tools.js";
+import { mockLLMEvent } from "./utils.js";
+
+await test("ollama", async (t) => {
+  await mockLLMEvent(t, "ollama");
+  await t.test("ollama function call", async (t) => {
+    const llm = new Ollama({
+      model: "llama3.2",
+    });
+    const chatResponse = await llm.chat({
+      messages: [
+        {
+          role: "user",
+          content: "What is the weather in Paris?",
+        },
+      ],
+      tools: [getWeatherTool],
+    });
+    if (
+      chatResponse.message.options &&
+      "toolCall" in chatResponse.message.options
+    ) {
+      assert.equal(chatResponse.message.options.toolCall.length, 1);
+      assert.equal(
+        chatResponse.message.options.toolCall[0]!.name,
+        getWeatherTool.metadata.name,
+      );
+    } else {
+      throw new Error("Expected tool calls in response");
+    }
+  });
+});

e2e/node/openai.e2e.ts

@@ -167,6 +167,7 @@ For questions about more specific sections, please use the vector_tool.`,
   const mockCall = t.mock.fn(({ query }: { query: string }) => {
     return originalCall({ query });
   });
+  // @ts-expect-error what?
   queryEngineTools[1]!.call = mockCall;
 
   const toolMapping = SimpleToolNodeMapping.fromObjects(queryEngineTools);

e2e/node/snapshot/ollama.snap

@@ -0,0 +1,37 @@
+{
+  "llmEventStart": [
+    {
+      "id": "PRESERVE_0",
+      "messages": [
+        {
+          "role": "user",
+          "content": "What is the weather in Paris?"
+        }
+      ]
+    }
+  ],
+  "llmEventEnd": [
+    {
+      "id": "PRESERVE_0",
+      "response": {
+        "message": {
+          "role": "assistant",
+          "content": "",
+          "options": {
+            "toolCall": [
+              {
+                "name": "getWeather",
+                "input": {
+                  "city": "Paris"
+                },
+                "id": "5d198775-5268-4552-993b-9ecb4425385b"
+              }
+            ]
+          }
+        },
+        "raw": null
+      }
+    }
+  ],
+  "llmEventStream": []
+}

e2e/package.json

@@ -12,10 +12,11 @@
     "@faker-js/faker": "^9.2.0",
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
+    "@llamaindex/ollama": "workspace:*",
     "@llamaindex/openai": "workspace:*",
     "@types/node": "^22.9.0",
     "@types/pg": "^8.11.8",
-    "@xenova/transformers": "^2.17.2",
+    "@huggingface/transformers": "^3.0.2",
     "consola": "^3.2.3",
     "dotenv": "^16.4.5",
     "llamaindex": "workspace:*",

examples/CHANGELOG.md

@@ -1,5 +1,18 @@
 # examples
 
+## 0.0.14
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+- Updated dependencies [fd8c882]
+  - llamaindex@0.8.10
+  - @llamaindex/core@0.4.7
+  - @llamaindex/workflow@0.0.4
+  - @llamaindex/readers@1.0.8
+
 ## 0.0.13
 
 ### Patch Changes

examples/package.json

@@ -1,15 +1,15 @@
 {
   "name": "@llamaindex/examples",
   "private": true,
-  "version": "0.0.13",
+  "version": "0.0.14",
   "dependencies": {
     "@aws-crypto/sha256-js": "^5.2.0",
     "@azure/cosmos": "^4.1.1",
     "@azure/identity": "^4.4.1",
     "@datastax/astra-db-ts": "^1.4.1",
-    "@llamaindex/core": "^0.4.5",
-    "@llamaindex/readers": "^1.0.6",
-    "@llamaindex/workflow": "^0.0.3",
+    "@llamaindex/core": "^0.4.7",
+    "@llamaindex/readers": "^1.0.8",
+    "@llamaindex/workflow": "^0.0.4",
     "@notionhq/client": "^2.2.15",
     "@pinecone-database/pinecone": "^3.0.2",
     "@vercel/postgres": "^0.10.0",
@@ -18,7 +18,7 @@
     "commander": "^12.1.0",
     "dotenv": "^16.4.5",
     "js-tiktoken": "^1.0.14",
-    "llamaindex": "^0.8.8",
+    "llamaindex": "^0.8.10",
     "mongodb": "^6.7.0",
     "pathe": "^1.1.2",
     "postgres": "^3.4.4"

examples/vectorIndexLocal.ts

@@ -14,7 +14,6 @@ Settings.llm = new Ollama({
 
 Settings.embedModel = new HuggingFaceEmbedding({
   modelType: "BAAI/bge-small-en-v1.5",
-  quantized: false,
 });
 
 async function main() {

examples/vllm.ts

@@ -0,0 +1,16 @@
+import { VLLM } from "llamaindex";
+
+const llm = new VLLM({
+  model: "NousResearch/Meta-Llama-3-8B-Instruct",
+});
+
+const response = await llm.chat({
+  messages: [
+    {
+      role: "user",
+      content: "Hello?",
+    },
+  ],
+});
+
+console.log(response.message.content);

examples/workflow/app-creator.ts

@@ -1,14 +1,19 @@
 import {
-  Context,
+  HandlerContext,
   StartEvent,
   StopEvent,
   Workflow,
   WorkflowEvent,
-} from "@llamaindex/core/workflow";
+} from "@llamaindex/workflow";
 import { OpenAI } from "llamaindex";
 
 const MAX_REVIEWS = 3;
 
+type Context = {
+  specification: string;
+  numberReviews: number;
+};
+
 // Using the o1-preview model (see https://platform.openai.com/docs/guides/reasoning?reasoning-prompt-examples=coding-planning)
 const llm = new OpenAI({ model: "o1-preview", temperature: 1 });
 
@@ -20,7 +25,9 @@ stores the question/answer pair in the database.`;
 
 // Create custom event types
 export class MessageEvent extends WorkflowEvent<{ msg: string }> {}
+
 export class CodeEvent extends WorkflowEvent<{ code: string }> {}
+
 export class ReviewEvent extends WorkflowEvent<{
   review: string;
   code: string;
@@ -34,12 +41,13 @@ const truncate = (str: string) => {
 };
 
 // the architect is responsible for writing the structure and the initial code based on the specification
-const architect = async (context: Context, ev: StartEvent) => {
-  // get the specification from the start event and save it to context
-  context.set("specification", ev.data.input);
-  const spec = context.get("specification");
+const architect = async (
+  context: HandlerContext<Context>,
+  _: StartEvent<string>,
+) => {
+  const spec = context.data.specification;
   // write a message to send an update to the user
-  context.writeEventToStream(
+  context.sendEvent(
     new MessageEvent({
       msg: `Writing app using this specification: ${truncate(spec)}`,
     }),
@@ -50,13 +58,13 @@ const architect = async (context: Context, ev: StartEvent) => {
 };
 
 // the coder is responsible for updating the code based on the review
-const coder = async (context: Context, ev: ReviewEvent) => {
+const coder = async (context: HandlerContext<Context>, ev: ReviewEvent) => {
   // get the specification from the context
-  const spec = context.get("specification");
+  const spec = context.data.specification;
   // get the latest review and code
   const { review, code } = ev.data;
   // write a message to send an update to the user
-  context.writeEventToStream(
+  context.sendEvent(
     new MessageEvent({
       msg: `Update code based on review: ${truncate(review)}`,
     }),
@@ -67,32 +75,35 @@ const coder = async (context: Context, ev: ReviewEvent) => {
 };
 
 // the reviewer is responsible for reviewing the code and providing feedback
-const reviewer = async (context: Context, ev: CodeEvent) => {
+const reviewer = async (context: HandlerContext<Context>, ev: CodeEvent) => {
   // get the specification from the context
-  const spec = context.get("specification");
+  const spec = context.data.specification;
   // get latest code from the event
   const { code } = ev.data;
   // update and check the number of reviews
-  const numberReviews = context.get("numberReviews", 0) + 1;
-  context.set("numberReviews", numberReviews);
-  if (numberReviews > MAX_REVIEWS) {
+  context.data.numberReviews++;
+  if (context.data.numberReviews > MAX_REVIEWS) {
     // the we've done this too many times - return the code
-    context.writeEventToStream(
+    context.sendEvent(
       new MessageEvent({
-        msg: `Already reviewed ${numberReviews - 1} times, stopping!`,
+        msg: `Already reviewed ${
+          context.data.numberReviews - 1
+        } times, stopping!`,
       }),
     );
     return new StopEvent({ result: code });
   }
   // write a message to send an update to the user
-  context.writeEventToStream(
-    new MessageEvent({ msg: `Review #${numberReviews}: ${truncate(code)}` }),
+  context.sendEvent(
+    new MessageEvent({
+      msg: `Review #${context.data.numberReviews}: ${truncate(code)}`,
+    }),
   );
   const prompt = `Review this code: <code>${code}</code>. Check if the code quality and whether it correctly implements this specification: <spec>${spec}</spec>. If you're satisfied, just return 'Looks great', nothing else. If not, return a review with a list of changes you'd like to see.`;
   const review = (await llm.complete({ prompt })).text;
   if (review.includes("Looks great")) {
     // the reviewer is satisfied with the code, let's return the review
-    context.writeEventToStream(
+    context.sendEvent(
       new MessageEvent({
         msg: `Reviewer says: ${review}`,
       }),
@@ -103,20 +114,44 @@ const reviewer = async (context: Context, ev: CodeEvent) => {
   return new ReviewEvent({ review, code });
 };
 
-const codeAgent = new Workflow({ validate: true });
-codeAgent.addStep(StartEvent, architect, { outputs: CodeEvent });
-codeAgent.addStep(ReviewEvent, coder, { outputs: CodeEvent });
-codeAgent.addStep(CodeEvent, reviewer, { outputs: ReviewEvent });
+const codeAgent = new Workflow<Context, string, string>();
+codeAgent.addStep(
+  {
+    inputs: [StartEvent<string>],
+    outputs: [CodeEvent],
+  },
+  architect,
+);
+codeAgent.addStep(
+  {
+    inputs: [ReviewEvent],
+    outputs: [CodeEvent],
+  },
+  coder,
+);
+codeAgent.addStep(
+  {
+    inputs: [CodeEvent],
+    outputs: [ReviewEvent, StopEvent],
+  },
+  reviewer,
+);
 
 // Usage
 async function main() {
-  const run = codeAgent.run(specification);
-  for await (const event of codeAgent.streamEvents()) {
-    const msg = (event as MessageEvent).data.msg;
-    console.log(`${msg}\n`);
+  const run = codeAgent.run(specification).with({
+    specification,
+    numberReviews: 0,
+  });
+  for await (const event of run) {
+    if (event instanceof MessageEvent) {
+      const msg = (event as MessageEvent).data.msg;
+      console.log(`${msg}\n`);
+    } else if (event instanceof StopEvent) {
+      const result = (event as StopEvent<string>).data;
+      console.log("Final code:\n", result);
+    }
   }
-  const result = await run;
-  console.log("Final code:\n", result.data.result);
 }
 
 main().catch(console.error);

examples/workflow/conditional.ts

@@ -1,10 +1,10 @@
 import {
-  Context,
+  HandlerContext,
   StartEvent,
   StopEvent,
   Workflow,
   WorkflowEvent,
-} from "@llamaindex/core/workflow";
+} from "@llamaindex/workflow";
 import { OpenAI } from "llamaindex";
 
 // Create LLM instance
@@ -12,59 +12,77 @@ const llm = new OpenAI();
 
 // Create custom event types
 export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
+
 export class CritiqueEvent extends WorkflowEvent<{ critique: string }> {}
+
 export class AnalysisEvent extends WorkflowEvent<{ analysis: string }> {}
 
-const generateJoke = async (_context: Context, ev: StartEvent) => {
-  const prompt = `Write your best joke about ${ev.data.input}.`;
+const generateJoke = async (_: unknown, ev: StartEvent<string>) => {
+  const prompt = `Write your best joke about ${ev.data}.`;
   const response = await llm.complete({ prompt });
   return new JokeEvent({ joke: response.text });
 };
 
-const critiqueJoke = async (_context: Context, ev: JokeEvent) => {
+const critiqueJoke = async (_: unknown, ev: JokeEvent) => {
   const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
   const response = await llm.complete({ prompt });
   return new CritiqueEvent({ critique: response.text });
 };
 
-const analyzeJoke = async (_context: Context, ev: JokeEvent) => {
+const analyzeJoke = async (_: unknown, ev: JokeEvent) => {
   const prompt = `Give a thorough analysis of the following joke: ${ev.data.joke}`;
   const response = await llm.complete({ prompt });
   return new AnalysisEvent({ analysis: response.text });
 };
 
 const reportJoke = async (
-  context: Context,
-  ev: AnalysisEvent | CritiqueEvent,
+  context: HandlerContext,
+  ev1: AnalysisEvent,
+  ev2: CritiqueEvent,
 ) => {
-  const events = context.collectEvents(ev, [AnalysisEvent, CritiqueEvent]);
-  if (!events) {
-    return;
-  }
-  const subPrompts = events.map((event) => {
-    if (event instanceof AnalysisEvent) {
-      return `Analysis: ${event.data.analysis}`;
-    } else if (event instanceof CritiqueEvent) {
-      return `Critique: ${event.data.critique}`;
-    }
-    return "";
-  });
+  const subPrompts = [ev1.data.analysis, ev2.data.critique];
 
-  const prompt = `Based on the following information about a joke:\n${subPrompts.join("\n")}\nProvide a comprehensive report on the joke's quality and impact.`;
+  const prompt = `Based on the following information about a joke:\n${subPrompts.join(
+    "\n",
+  )}\nProvide a comprehensive report on the joke's quality and impact.`;
   const response = await llm.complete({ prompt });
-  return new StopEvent({ result: response.text });
+  return new StopEvent(response.text);
 };
 
-const jokeFlow = new Workflow();
-jokeFlow.addStep(StartEvent, generateJoke);
-jokeFlow.addStep(JokeEvent, critiqueJoke);
-jokeFlow.addStep(JokeEvent, analyzeJoke);
-jokeFlow.addStep([AnalysisEvent, CritiqueEvent], reportJoke);
+const jokeFlow = new Workflow<unknown, string, string>();
+jokeFlow.addStep(
+  {
+    inputs: [StartEvent<string>],
+    outputs: [JokeEvent],
+  },
+  generateJoke,
+);
+jokeFlow.addStep(
+  {
+    inputs: [JokeEvent],
+    outputs: [CritiqueEvent],
+  },
+  critiqueJoke,
+);
+jokeFlow.addStep(
+  {
+    inputs: [JokeEvent],
+    outputs: [AnalysisEvent],
+  },
+  analyzeJoke,
+);
+jokeFlow.addStep(
+  {
+    inputs: [AnalysisEvent, CritiqueEvent],
+    outputs: [StopEvent<string>],
+  },
+  reportJoke,
+);
 
 // Usage
 async function main() {
   const result = await jokeFlow.run("pirates");
-  console.log(result.data.result);
+  console.log(result.data);
 }
 
 main().catch(console.error);

examples/workflow/joke.ts

@@ -1,10 +1,9 @@
 import {
-  Context,
   StartEvent,
   StopEvent,
   Workflow,
   WorkflowEvent,
-} from "@llamaindex/core/workflow";
+} from "@llamaindex/workflow";
 import { OpenAI } from "llamaindex";
 
 // Create LLM instance
@@ -13,26 +12,38 @@ const llm = new OpenAI();
 // Create a custom event type
 export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
 
-const generateJoke = async (_context: Context, ev: StartEvent) => {
-  const prompt = `Write your best joke about ${ev.data.input}.`;
+const generateJoke = async (_: unknown, ev: StartEvent<string>) => {
+  const prompt = `Write your best joke about ${ev.data}.`;
   const response = await llm.complete({ prompt });
   return new JokeEvent({ joke: response.text });
 };
 
-const critiqueJoke = async (_context: Context, ev: JokeEvent) => {
+const critiqueJoke = async (_: unknown, ev: JokeEvent) => {
   const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
   const response = await llm.complete({ prompt });
-  return new StopEvent({ result: response.text });
+  return new StopEvent(response.text);
 };
 
-const jokeFlow = new Workflow({ verbose: true });
-jokeFlow.addStep(StartEvent, generateJoke);
-jokeFlow.addStep(JokeEvent, critiqueJoke);
+const jokeFlow = new Workflow<unknown, string, string>();
+jokeFlow.addStep(
+  {
+    inputs: [StartEvent<string>],
+    outputs: [JokeEvent],
+  },
+  generateJoke,
+);
+jokeFlow.addStep(
+  {
+    inputs: [JokeEvent],
+    outputs: [StopEvent<string>],
+  },
+  critiqueJoke,
+);
 
 // Usage
 async function main() {
   const result = await jokeFlow.run("pirates");
-  console.log(result.data.result);
+  console.log(result.data);
 }
 
 main().catch(console.error);

examples/workflow/stream-events.ts

@@ -1,10 +1,10 @@
 import {
-  Context,
+  HandlerContext,
   StartEvent,
   StopEvent,
   Workflow,
   WorkflowEvent,
-} from "@llamaindex/core/workflow";
+} from "@llamaindex/workflow";
 import { OpenAI } from "llamaindex";
 
 // Create LLM instance
@@ -12,38 +12,55 @@ const llm = new OpenAI();
 
 // Create custom event types
 export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
+
 export class MessageEvent extends WorkflowEvent<{ msg: string }> {}
 
-const generateJoke = async (context: Context, ev: StartEvent) => {
-  context.writeEventToStream(
-    new MessageEvent({ msg: `Generating a joke about: ${ev.data.input}` }),
+const generateJoke = async (context: HandlerContext, ev: StartEvent) => {
+  context.sendEvent(
+    new MessageEvent({ msg: `Generating a joke about: ${ev.data}` }),
   );
-  const prompt = `Write your best joke about ${ev.data.input}.`;
+  const prompt = `Write your best joke about ${ev.data}.`;
   const response = await llm.complete({ prompt });
   return new JokeEvent({ joke: response.text });
 };
 
-const critiqueJoke = async (context: Context, ev: JokeEvent) => {
-  context.writeEventToStream(
+const critiqueJoke = async (context: HandlerContext, ev: JokeEvent) => {
+  context.sendEvent(
     new MessageEvent({ msg: `Write a critique of this joke: ${ev.data.joke}` }),
   );
   const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
   const response = await llm.complete({ prompt });
-  return new StopEvent({ result: response.text });
+  return new StopEvent(response.text);
 };
 
 const jokeFlow = new Workflow();
-jokeFlow.addStep(StartEvent, generateJoke);
-jokeFlow.addStep(JokeEvent, critiqueJoke);
+jokeFlow.addStep(
+  {
+    inputs: [StartEvent<string>],
+    outputs: [JokeEvent],
+  },
+  generateJoke,
+);
+jokeFlow.addStep(
+  {
+    inputs: [JokeEvent],
+    outputs: [StopEvent<string>],
+  },
+  critiqueJoke,
+);
 
 // Usage
 async function main() {
   const run = jokeFlow.run("pirates");
-  for await (const event of jokeFlow.streamEvents()) {
-    console.log((event as MessageEvent).data.msg);
+  for await (const event of run) {
+    if (event instanceof MessageEvent) {
+      console.log("Message:");
+      console.log((event as MessageEvent).data.msg);
+    } else if (event instanceof StopEvent) {
+      console.log("Result:");
+      console.log((event as StopEvent<string>).data);
+    }
   }
-  const result = await run;
-  console.log(result.data.result);
 }
 
 main().catch(console.error);

examples/workflow/timeout.ts

@@ -1,19 +1,21 @@
-import {
-  Context,
-  StartEvent,
-  StopEvent,
-  Workflow,
-} from "@llamaindex/core/workflow";
+import { StartEvent, StopEvent, Workflow } from "@llamaindex/workflow";
 
-const longRunning = async (_context: Context, ev: StartEvent) => {
+const longRunning = async (_: unknown, ev: StartEvent<string>) => {
   await new Promise((resolve) => setTimeout(resolve, 2000)); // Wait for 2 seconds
-  return new StopEvent({ result: "We waited 2 seconds" });
+  return new StopEvent("We waited 2 seconds");
 };
 
 async function timeout() {
-  const workflow = new Workflow({ verbose: true, timeout: 1 });
-  workflow.addStep(StartEvent, longRunning);
-  // This will timeout
+  const workflow = new Workflow<unknown, string, string>({
+    timeout: 1,
+  });
+  workflow.addStep(
+    {
+      inputs: [StartEvent<string>],
+      outputs: [StopEvent<string>],
+    },
+    longRunning,
+  );
   try {
     await workflow.run("Let's start");
   } catch (error) {
@@ -23,14 +25,23 @@ async function timeout() {
 
 async function notimeout() {
   // Increase timeout to 3 seconds - no timeout
-  const workflow = new Workflow({ verbose: true, timeout: 3 });
-  workflow.addStep(StartEvent, longRunning);
+  const workflow = new Workflow<unknown, string, string>({
+    timeout: 3,
+  });
+  workflow.addStep(
+    {
+      inputs: [StartEvent<string>],
+      outputs: [StopEvent<string>],
+    },
+    longRunning,
+  );
   const result = await workflow.run("Let's start");
-  console.log(result.data.result);
+  console.log(result.data);
 }
 
 async function main() {
   await timeout();
+  console.log("---");
   await notimeout();
 }
 

examples/workflow/validation.ts

@@ -1,10 +1,9 @@
 import {
-  Context,
   StartEvent,
   StopEvent,
   Workflow,
   WorkflowEvent,
-} from "@llamaindex/core/workflow";
+} from "@llamaindex/workflow";
 import { OpenAI } from "llamaindex";
 
 // Create LLM instance
@@ -13,40 +12,66 @@ const llm = new OpenAI();
 // Create a custom event type
 export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
 
-const generateJoke = async (_context: Context, ev: StartEvent) => {
-  const prompt = `Write your best joke about ${ev.data.input}.`;
+const generateJoke = async (_: unknown, ev: StartEvent<string>) => {
+  const prompt = `Write your best joke about ${ev.data}.`;
   const response = await llm.complete({ prompt });
   return new JokeEvent({ joke: response.text });
 };
 
-const critiqueJoke = async (_context: Context, ev: JokeEvent) => {
+const critiqueJoke = async (_: unknown, ev: JokeEvent) => {
   const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
   const response = await llm.complete({ prompt });
-  return new StopEvent({ result: response.text });
+  return new StopEvent(response.text);
 };
 
 async function validateFails() {
   try {
-    const jokeFlow = new Workflow({ verbose: true, validate: true });
-    jokeFlow.addStep(StartEvent, generateJoke, { outputs: StopEvent });
-    jokeFlow.addStep(JokeEvent, critiqueJoke, { outputs: StopEvent });
-    await jokeFlow.run("pirates");
+    const jokeFlow = new Workflow();
+    jokeFlow.addStep(
+      {
+        inputs: [StartEvent<string>],
+        outputs: [StopEvent<string>],
+      },
+      // @ts-expect-error outputs should be JokeEvent
+      generateJoke,
+    );
+    jokeFlow.addStep(
+      {
+        inputs: [JokeEvent],
+        outputs: [StopEvent],
+      },
+      critiqueJoke,
+    );
+    await jokeFlow.run("pirates").strict();
   } catch (e) {
     console.error("Validation failed:", e);
   }
 }
 
 async function validate() {
-  const jokeFlow = new Workflow({ verbose: true, validate: true });
-  jokeFlow.addStep(StartEvent, generateJoke, { outputs: JokeEvent });
-  jokeFlow.addStep(JokeEvent, critiqueJoke, { outputs: StopEvent });
-  const result = await jokeFlow.run("pirates");
-  console.log(result.data.result);
+  const jokeFlow = new Workflow();
+  jokeFlow.addStep(
+    {
+      inputs: [StartEvent<string>],
+      outputs: [JokeEvent],
+    },
+    generateJoke,
+  );
+  jokeFlow.addStep(
+    {
+      inputs: [JokeEvent],
+      outputs: [StopEvent<string>],
+    },
+    critiqueJoke,
+  );
+  const result = await jokeFlow.run("pirates").strict();
+  console.log(result.data);
 }
 
 // Usage
 async function main() {
   await validateFails();
+  console.log("---");
   await validate();
 }
 

package.json

@@ -35,12 +35,6 @@
     "typescript-eslint": "^8.13.0"
   },
   "packageManager": "pnpm@9.12.3",
-  "pnpm": {
-    "overrides": {
-      "trim": "1.0.1",
-      "protobufjs": "7.2.6"
-    }
-  },
   "lint-staged": {
     "(!apps/docs/i18n/**/docusaurus-plugin-content-docs/current/api/*).{js,jsx,ts,tsx,md}": "prettier --write"
   }

packages/autotool/CHANGELOG.md

@@ -1,5 +1,32 @@
 # @llamaindex/autotool
 
+## 5.0.12
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
+## 5.0.11
+
+### Patch Changes
+
+- llamaindex@0.8.11
+
+## 5.0.10
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+
+## 5.0.9
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+
 ## 5.0.8
 
 ### Patch Changes

packages/autotool/examples/01_node/CHANGELOG.md

@@ -1,5 +1,36 @@
 # @llamaindex/autotool-01-node-example
 
+## 0.0.55
+
+### Patch Changes
+
+- llamaindex@0.8.12
+- @llamaindex/autotool@5.0.12
+
+## 0.0.54
+
+### Patch Changes
+
+- llamaindex@0.8.11
+- @llamaindex/autotool@5.0.11
+
+## 0.0.53
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+  - @llamaindex/autotool@5.0.10
+
+## 0.0.52
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+  - @llamaindex/autotool@5.0.9
+
 ## 0.0.51
 
 ### Patch Changes

packages/autotool/examples/01_node/package.json

@@ -13,5 +13,5 @@
   "scripts": {
     "start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
   },
-  "version": "0.0.51"
+  "version": "0.0.55"
 }

packages/autotool/examples/02_nextjs/CHANGELOG.md

@@ -1,5 +1,36 @@
 # @llamaindex/autotool-02-next-example
 
+## 0.1.99
+
+### Patch Changes
+
+- llamaindex@0.8.12
+- @llamaindex/autotool@5.0.12
+
+## 0.1.98
+
+### Patch Changes
+
+- llamaindex@0.8.11
+- @llamaindex/autotool@5.0.11
+
+## 0.1.97
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+  - @llamaindex/autotool@5.0.10
+
+## 0.1.96
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+  - @llamaindex/autotool@5.0.9
+
 ## 0.1.95
 
 ### Patch Changes

packages/autotool/examples/02_nextjs/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool-02-next-example",
   "private": true,
-  "version": "0.1.95",
+  "version": "0.1.99",
   "scripts": {
     "dev": "next dev",
     "build": "next build",

packages/autotool/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/autotool",
   "type": "module",
-  "version": "5.0.8",
+  "version": "5.0.12",
   "description": "auto transpile your JS function to LLM Agent compatible",
   "files": [
     "dist",

packages/cloud/CHANGELOG.md

@@ -1,5 +1,35 @@
 # @llamaindex/cloud
 
+## 2.0.9
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
+## 2.0.8
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+
+## 2.0.7
+
+### Patch Changes
+
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+  - @llamaindex/core@0.4.7
+
+## 2.0.6
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/core@0.4.6
+
 ## 2.0.5
 
 ### Patch Changes

packages/cloud/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/cloud",
-  "version": "2.0.5",
+  "version": "2.0.9",
   "type": "module",
   "license": "MIT",
   "scripts": {

packages/community/CHANGELOG.md

@@ -1,5 +1,35 @@
 # @llamaindex/community
 
+## 0.0.67
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
+## 0.0.66
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+
+## 0.0.65
+
+### Patch Changes
+
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+  - @llamaindex/core@0.4.7
+
+## 0.0.64
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/core@0.4.6
+
 ## 0.0.63
 
 ### Patch Changes

packages/community/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/community",
   "description": "Community package for LlamaIndexTS",
-  "version": "0.0.63",
+  "version": "0.0.67",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/core/CHANGELOG.md

@@ -1,5 +1,31 @@
 # @llamaindex/core
 
+## 0.4.9
+
+### Patch Changes
+
+- 7ae6eaa: feat: allow pass `additionalChatOptions` to agent
+
+## 0.4.8
+
+### Patch Changes
+
+- f865c98: feat: async get message on chat store
+
+## 0.4.7
+
+### Patch Changes
+
+- d89ebe0: feat: better support for zod schema
+- fd8c882: chore: add warning on legacy workflow API
+
+## 0.4.6
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+
 ## 0.4.5
 
 ### Patch Changes

packages/core/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/core",
   "type": "module",
-  "version": "0.4.5",
+  "version": "0.4.9",
   "description": "LlamaIndex Core Module",
   "exports": {
     "./agent": {

packages/core/src/agent/base.ts

@@ -106,11 +106,17 @@ export type AgentRunnerParams<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = {
   llm: AI;
   chatHistory: ChatMessage<AdditionalMessageOptions>[];
   systemPrompt: MessageContent | null;
-  runner: AgentWorker<AI, Store, AdditionalMessageOptions>;
+  runner: AgentWorker<
+    AI,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
   tools:
     | BaseToolWithCall[]
     | ((query: MessageContent) => Promise<BaseToolWithCall[]>);
@@ -125,6 +131,7 @@ export type AgentParamsBase<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > =
   | {
       llm?: AI;
@@ -132,6 +139,7 @@ export type AgentParamsBase<
       systemPrompt?: MessageContent;
       verbose?: boolean;
       tools: BaseToolWithCall[];
+      additionalChatOptions?: AdditionalChatOptions;
     }
   | {
       llm?: AI;
@@ -139,6 +147,7 @@ export type AgentParamsBase<
       systemPrompt?: MessageContent;
       verbose?: boolean;
       toolRetriever: ObjectRetriever<BaseToolWithCall>;
+      additionalChatOptions?: AdditionalChatOptions;
     };
 
 /**
@@ -153,21 +162,36 @@ export abstract class AgentWorker<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > {
-  #taskSet = new Set<TaskStep<AI, Store, AdditionalMessageOptions>>();
-  abstract taskHandler: TaskHandler<AI, Store, AdditionalMessageOptions>;
+  #taskSet = new Set<
+    TaskStep<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
+  >();
+  abstract taskHandler: TaskHandler<
+    AI,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
 
   public createTask(
     query: MessageContent,
-    context: AgentTaskContext<AI, Store, AdditionalMessageOptions>,
-  ): ReadableStream<TaskStepOutput<AI, Store, AdditionalMessageOptions>> {
+    context: AgentTaskContext<
+      AI,
+      Store,
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
+  ): ReadableStream<
+    TaskStepOutput<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
+  > {
     context.store.messages.push({
       role: "user",
       content: query,
     });
     const taskOutputStream = createTaskOutputStream(this.taskHandler, context);
     return new ReadableStream<
-      TaskStepOutput<AI, Store, AdditionalMessageOptions>
+      TaskStepOutput<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
     >({
       start: async (controller) => {
         for await (const stepOutput of taskOutputStream) {
@@ -176,7 +200,8 @@ export abstract class AgentWorker<
             let currentStep: TaskStep<
               AI,
               Store,
-              AdditionalMessageOptions
+              AdditionalMessageOptions,
+              AdditionalChatOptions
             > | null = stepOutput.taskStep;
             while (currentStep) {
               this.#taskSet.delete(currentStep);
@@ -227,6 +252,7 @@ export abstract class AgentRunner<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > extends BaseChatEngine {
   readonly #llm: AI;
   readonly #tools:
@@ -234,7 +260,12 @@ export abstract class AgentRunner<
     | ((query: MessageContent) => Promise<BaseToolWithCall[]>);
   readonly #systemPrompt: MessageContent | null = null;
   #chatHistory: ChatMessage<AdditionalMessageOptions>[];
-  readonly #runner: AgentWorker<AI, Store, AdditionalMessageOptions>;
+  readonly #runner: AgentWorker<
+    AI,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
   readonly #verbose: boolean;
 
   // create extra store
@@ -245,7 +276,7 @@ export abstract class AgentRunner<
   }
 
   static defaultTaskHandler: TaskHandler<LLM> = async (step, enqueueOutput) => {
-    const { llm, getTools, stream } = step.context;
+    const { llm, getTools, stream, additionalChatOptions } = step.context;
     const lastMessage = step.context.store.messages.at(-1)!.content;
     const tools = await getTools(lastMessage);
     if (!stream) {
@@ -253,8 +284,9 @@ export abstract class AgentRunner<
         stream,
         tools,
         messages: [...step.context.store.messages],
+        additionalChatOptions,
       });
-      await stepTools<LLM>({
+      await stepTools({
         response,
         tools,
         step,
@@ -265,6 +297,7 @@ export abstract class AgentRunner<
         stream,
         tools,
         messages: [...step.context.store.messages],
+        additionalChatOptions,
       });
       await stepToolsStreaming<LLM>({
         response,
@@ -276,7 +309,12 @@ export abstract class AgentRunner<
   };
 
   protected constructor(
-    params: AgentRunnerParams<AI, Store, AdditionalMessageOptions>,
+    params: AgentRunnerParams<
+      AI,
+      Store,
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
   ) {
     super();
     const { llm, chatHistory, systemPrompt, runner, tools, verbose } = params;
@@ -330,6 +368,7 @@ export abstract class AgentRunner<
     stream: boolean = false,
     verbose: boolean | undefined = undefined,
     chatHistory?: ChatMessage<AdditionalMessageOptions>[],
+    additionalChatOptions?: AdditionalChatOptions,
   ) {
     const initialMessages = [...(chatHistory ?? this.#chatHistory)];
     if (this.#systemPrompt !== null) {
@@ -348,6 +387,7 @@ export abstract class AgentRunner<
       stream,
       toolCallCount: 0,
       llm: this.#llm,
+      additionalChatOptions: additionalChatOptions ?? {},
       getTools: (message) => this.getTools(message),
       store: {
         ...this.createStore(),
@@ -365,13 +405,29 @@ export abstract class AgentRunner<
     });
   }
 
-  async chat(params: NonStreamingChatEngineParams): Promise<EngineResponse>;
   async chat(
-    params: StreamingChatEngineParams,
+    params: NonStreamingChatEngineParams<
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
+  ): Promise<EngineResponse>;
+  async chat(
+    params: StreamingChatEngineParams<
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
   ): Promise<ReadableStream<EngineResponse>>;
   @wrapEventCaller
   async chat(
-    params: NonStreamingChatEngineParams | StreamingChatEngineParams,
+    params:
+      | NonStreamingChatEngineParams<
+          AdditionalMessageOptions,
+          AdditionalChatOptions
+        >
+      | StreamingChatEngineParams<
+          AdditionalMessageOptions,
+          AdditionalChatOptions
+        >,
   ): Promise<EngineResponse | ReadableStream<EngineResponse>> {
     let chatHistory: ChatMessage<AdditionalMessageOptions>[] = [];
 
@@ -388,6 +444,7 @@ export abstract class AgentRunner<
       !!params.stream,
       false,
       chatHistory,
+      params.chatOptions,
     );
     for await (const stepOutput of task) {
       // update chat history for each round
@@ -398,7 +455,12 @@ export abstract class AgentRunner<
           return output.pipeThrough(
             new TransformStream<EngineResponse>({
               transform(chunk, controller) {
-                controller.enqueue(EngineResponse.fromChatResponseChunk(chunk));
+                controller.enqueue(
+                  EngineResponse.fromChatResponseChunk(
+                    chunk,
+                    chunk.sourceNodes,
+                  ),
+                );
               },
             }),
           );

packages/core/src/agent/llm.ts

@@ -4,24 +4,66 @@ import { ObjectRetriever } from "../objects";
 import { AgentRunner, AgentWorker, type AgentParamsBase } from "./base.js";
 import { validateAgentParams } from "./utils.js";
 
-type LLMParamsBase = AgentParamsBase<LLM>;
+type LLMParamsBase<
+  AI extends LLM,
+  AdditionalMessageOptions extends object = AI extends LLM<
+    object,
+    infer AdditionalMessageOptions
+  >
+    ? AdditionalMessageOptions
+    : never,
+  AdditionalChatOptions extends object = object,
+> = AgentParamsBase<AI, AdditionalMessageOptions, AdditionalChatOptions>;
 
-type LLMParamsWithTools = LLMParamsBase & {
+type LLMParamsWithTools<
+  AI extends LLM,
+  AdditionalMessageOptions extends object = AI extends LLM<
+    object,
+    infer AdditionalMessageOptions
+  >
+    ? AdditionalMessageOptions
+    : never,
+  AdditionalChatOptions extends object = object,
+> = LLMParamsBase<AI, AdditionalMessageOptions, AdditionalChatOptions> & {
   tools: BaseToolWithCall[];
 };
 
-type LLMParamsWithToolRetriever = LLMParamsBase & {
+type LLMParamsWithToolRetriever<
+  AI extends LLM,
+  AdditionalMessageOptions extends object = AI extends LLM<
+    object,
+    infer AdditionalMessageOptions
+  >
+    ? AdditionalMessageOptions
+    : never,
+  AdditionalChatOptions extends object = object,
+> = LLMParamsBase<AI, AdditionalMessageOptions, AdditionalChatOptions> & {
   toolRetriever: ObjectRetriever<BaseToolWithCall>;
 };
 
-export type LLMAgentParams = LLMParamsWithTools | LLMParamsWithToolRetriever;
+export type LLMAgentParams<
+  AI extends LLM,
+  AdditionalMessageOptions extends object = AI extends LLM<
+    object,
+    infer AdditionalMessageOptions
+  >
+    ? AdditionalMessageOptions
+    : never,
+  AdditionalChatOptions extends object = object,
+> =
+  | LLMParamsWithTools<AI, AdditionalMessageOptions, AdditionalChatOptions>
+  | LLMParamsWithToolRetriever<
+      AI,
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >;
 
 export class LLMAgentWorker extends AgentWorker<LLM> {
   taskHandler = AgentRunner.defaultTaskHandler;
 }
 
 export class LLMAgent extends AgentRunner<LLM> {
-  constructor(params: LLMAgentParams) {
+  constructor(params: LLMAgentParams<LLM>) {
     validateAgentParams(params);
     const llm = params.llm ?? (Settings.llm ? (Settings.llm as LLM) : null);
     if (!llm)

packages/core/src/agent/types.ts

@@ -19,6 +19,7 @@ export type AgentTaskContext<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = {
   readonly stream: boolean;
   readonly toolCallCount: number;
@@ -26,6 +27,7 @@ export type AgentTaskContext<
   readonly getTools: (
     input: MessageContent,
   ) => BaseToolWithCall[] | Promise<BaseToolWithCall[]>;
+  readonly additionalChatOptions: Partial<AdditionalChatOptions>;
   shouldContinue: (
     taskStep: Readonly<TaskStep<Model, Store, AdditionalMessageOptions>>,
   ) => boolean;
@@ -45,13 +47,26 @@ export type TaskStep<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = {
   id: UUID;
-  context: AgentTaskContext<Model, Store, AdditionalMessageOptions>;
+  context: AgentTaskContext<
+    Model,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
 
   // linked list
-  prevStep: TaskStep<Model, Store, AdditionalMessageOptions> | null;
-  nextSteps: Set<TaskStep<Model, Store, AdditionalMessageOptions>>;
+  prevStep: TaskStep<
+    Model,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  > | null;
+  nextSteps: Set<
+    TaskStep<Model, Store, AdditionalMessageOptions, AdditionalChatOptions>
+  >;
 };
 
 export type TaskStepOutput<
@@ -63,8 +78,14 @@ export type TaskStepOutput<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = {
-  taskStep: TaskStep<Model, Store, AdditionalMessageOptions>;
+  taskStep: TaskStep<
+    Model,
+    Store,
+    AdditionalMessageOptions,
+    AdditionalChatOptions
+  >;
   // output shows the response to the user
   output:
     | ChatResponse<AdditionalMessageOptions>
@@ -81,10 +102,16 @@ export type TaskHandler<
   >
     ? AdditionalMessageOptions
     : never,
+  AdditionalChatOptions extends object = object,
 > = (
-  step: TaskStep<Model, Store, AdditionalMessageOptions>,
+  step: TaskStep<Model, Store, AdditionalMessageOptions, AdditionalChatOptions>,
   enqueueOutput: (
-    taskOutput: TaskStepOutput<Model, Store, AdditionalMessageOptions>,
+    taskOutput: TaskStepOutput<
+      Model,
+      Store,
+      AdditionalMessageOptions,
+      AdditionalChatOptions
+    >,
   ) => void,
 ) => Promise<void>;
 

packages/core/src/chat-engine/base.ts

@@ -16,14 +16,18 @@ export interface BaseChatEngineParams<
 
 export interface StreamingChatEngineParams<
   AdditionalMessageOptions extends object = object,
+  AdditionalChatOptions extends object = object,
 > extends BaseChatEngineParams<AdditionalMessageOptions> {
   stream: true;
+  chatOptions?: AdditionalChatOptions;
 }
 
 export interface NonStreamingChatEngineParams<
   AdditionalMessageOptions extends object = object,
+  AdditionalChatOptions extends object = object,
 > extends BaseChatEngineParams<AdditionalMessageOptions> {
   stream?: false;
+  chatOptions?: AdditionalChatOptions;
 }
 
 export abstract class BaseChatEngine {

packages/core/src/llms/base.ts

@@ -1,5 +1,4 @@
-import { streamConverter } from "../utils";
-import { extractText } from "../utils/llms";
+import { extractText, streamConverter } from "../utils";
 import type {
   ChatResponse,
   ChatResponseChunk,

packages/core/src/memory/base.ts

@@ -65,7 +65,9 @@ export abstract class BaseChatStoreMemory<
     super();
   }
 
-  getAllMessages(): ChatMessage<AdditionalMessageOptions>[] {
+  getAllMessages():
+    | ChatMessage<AdditionalMessageOptions>[]
+    | Promise<ChatMessage<AdditionalMessageOptions>[]> {
     return this.chatStore.getMessages(this.chatStoreKey);
   }
 

packages/core/src/memory/chat-memory-buffer.ts

@@ -33,11 +33,11 @@ export class ChatMemoryBuffer<
     }
   }
 
-  getMessages(
+  async getMessages(
     transientMessages?: ChatMessage<AdditionalMessageOptions>[] | undefined,
     initialTokenCount: number = 0,
   ) {
-    const messages = this.getAllMessages();
+    const messages = await this.getAllMessages();
 
     if (initialTokenCount > this.tokenLimit) {
       throw new Error("Initial token count exceeds token limit");

packages/core/src/storage/chat-store/base-chat-store.ts

@@ -7,7 +7,11 @@ export abstract class BaseChatStore<
     key: string,
     messages: ChatMessage<AdditionalMessageOptions>[],
   ): void;
-  abstract getMessages(key: string): ChatMessage<AdditionalMessageOptions>[];
+  abstract getMessages(
+    key: string,
+  ):
+    | ChatMessage<AdditionalMessageOptions>[]
+    | Promise<ChatMessage<AdditionalMessageOptions>[]>;
   abstract addMessage(
     key: string,
     message: ChatMessage<AdditionalMessageOptions>,

packages/core/src/tools/function-tool.ts

@@ -4,18 +4,12 @@ import { zodToJsonSchema } from "zod-to-json-schema";
 import type { JSONValue } from "../global";
 import type { BaseTool, ToolMetadata } from "../llms";
 
-const kOriginalFn = Symbol("originalFn");
-
 export class FunctionTool<T, R extends JSONValue | Promise<JSONValue>>
   implements BaseTool<T>
 {
-  [kOriginalFn]?: (input: T) => R;
-
   #fn: (input: T) => R;
-  #metadata: ToolMetadata<JSONSchemaType<T>>;
-  // todo: for the future, we can use zod to validate the input parameters
-  // eslint-disable-next-line no-unused-private-class-members
-  #zodType: z.ZodType<T> | null = null;
+  readonly #metadata: ToolMetadata<JSONSchemaType<T>>;
+  readonly #zodType: z.ZodType<T> | null = null;
   constructor(
     fn: (input: T) => R,
     metadata: ToolMetadata<JSONSchemaType<T>>,
@@ -32,6 +26,12 @@ export class FunctionTool<T, R extends JSONValue | Promise<JSONValue>>
     fn: (input: T) => JSONValue | Promise<JSONValue>,
     schema: ToolMetadata<JSONSchemaType<T>>,
   ): FunctionTool<T, JSONValue | Promise<JSONValue>>;
+  static from<R extends z.ZodType>(
+    fn: (input: z.infer<R>) => JSONValue | Promise<JSONValue>,
+    schema: Omit<ToolMetadata, "parameters"> & {
+      parameters: R;
+    },
+  ): FunctionTool<z.infer<R>, JSONValue | Promise<JSONValue>>;
   static from<T, R extends z.ZodType<T>>(
     fn: (input: T) => JSONValue | Promise<JSONValue>,
     schema: Omit<ToolMetadata, "parameters"> & {
@@ -40,15 +40,15 @@ export class FunctionTool<T, R extends JSONValue | Promise<JSONValue>>
   ): FunctionTool<T, JSONValue>;
   // eslint-disable-next-line @typescript-eslint/no-explicit-any
   static from(fn: any, schema: any): any {
-    if (schema.parameter instanceof z.ZodSchema) {
-      const jsonSchema = zodToJsonSchema(schema.parameter);
+    if (schema.parameters instanceof z.ZodSchema) {
+      const jsonSchema = zodToJsonSchema(schema.parameters);
       return new FunctionTool(
         fn,
         {
           ...schema,
           parameters: jsonSchema,
         },
-        schema.parameter,
+        schema.parameters,
       );
     }
     return new FunctionTool(fn, schema);
@@ -58,7 +58,15 @@ export class FunctionTool<T, R extends JSONValue | Promise<JSONValue>>
     return this.#metadata as BaseTool<T>["metadata"];
   }
 
-  call(input: T) {
+  call = (input: T) => {
+    if (this.#zodType) {
+      const result = this.#zodType.safeParse(input);
+      if (result.success) {
+        return this.#fn.call(null, result.data);
+      } else {
+        console.warn(result.error.errors);
+      }
+    }
     return this.#fn.call(null, input);
-  }
+  };
 }

packages/core/src/workflow/workflow.ts

@@ -13,6 +13,8 @@ export type StepFunction<T extends WorkflowEvent = WorkflowEvent> = (
 
 type EventTypeParam = EventTypes | EventTypes[];
 
+let once = false;
+
 export class Workflow {
   #steps: Map<
     // eslint-disable-next-line @typescript-eslint/no-explicit-any
@@ -29,8 +31,20 @@ export class Workflow {
       verbose?: boolean;
       timeout?: number;
       validate?: boolean;
+      ignoreDeprecatedWarning?: boolean;
     } = {},
   ) {
+    if (!once && !params.ignoreDeprecatedWarning) {
+      console.warn(
+        "@llamaindex/core/workflow is going to use the new workflow API in the next major version.",
+        "Please update your imports to @llamaindex/workflow",
+      );
+      console.warn(
+        "See https://ts.llamaindex.ai/docs/llamaindex/guide/workflow for more information",
+      );
+      once = true;
+    }
+
     this.#verbose = params.verbose ?? false;
     this.#timeout = params.timeout ?? null;
     this.#validate = params.validate ?? false;

packages/core/tests/memory/chat-memory-buffer.test.ts

@@ -19,7 +19,7 @@ describe("ChatMemoryBuffer", () => {
     expect(buffer.tokenLimit).toBe(500);
   });
 
-  test("getMessages returns all messages when under token limit", () => {
+  test("getMessages returns all messages when under token limit", async () => {
     const messages: ChatMessage[] = [
       { role: "user", content: "Hello" },
       { role: "assistant", content: "Hi there!" },
@@ -30,11 +30,11 @@ describe("ChatMemoryBuffer", () => {
       chatHistory: messages,
     });
 
-    const result = buffer.getMessages();
+    const result = await buffer.getMessages();
     expect(result).toEqual(messages);
   });
 
-  test("getMessages truncates messages when over token limit", () => {
+  test("getMessages truncates messages when over token limit", async () => {
     const messages: ChatMessage[] = [
       { role: "user", content: "This is a long message" },
       { role: "assistant", content: "This is also a long reply" },
@@ -45,11 +45,11 @@ describe("ChatMemoryBuffer", () => {
       chatHistory: messages,
     });
 
-    const result = buffer.getMessages();
+    const result = await buffer.getMessages();
     expect(result).toEqual([{ role: "user", content: "Short" }]);
   });
 
-  test("getMessages handles input messages", () => {
+  test("getMessages handles input messages", async () => {
     const storedMessages: ChatMessage[] = [
       { role: "user", content: "Hello" },
       { role: "assistant", content: "Hi there!" },
@@ -62,13 +62,13 @@ describe("ChatMemoryBuffer", () => {
     const inputMessages: ChatMessage[] = [
       { role: "user", content: "New message" },
     ];
-    const result = buffer.getMessages(inputMessages);
+    const result = await buffer.getMessages(inputMessages);
     expect(result).toEqual([...inputMessages, ...storedMessages]);
   });
 
   test("getMessages throws error when initial token count exceeds limit", () => {
     const buffer = new ChatMemoryBuffer({ tokenLimit: 10 });
-    expect(() => buffer.getMessages(undefined, 20)).toThrow(
+    expect(async () => buffer.getMessages(undefined, 20)).rejects.toThrow(
       "Initial token count exceeds token limit",
     );
   });

packages/env/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @llamaindex/env
 
+## 0.1.20
+
+### Patch Changes
+
+- 4fc001c: chore: bump `@huggingface/transformers`
+
+  Upgrade to v3, please read https://github.com/huggingface/transformers.js/releases/tag/3.0.0 for more information.
+
 ## 0.1.19
 
 ### Patch Changes

packages/env/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/env",
   "description": "environment wrapper, supports all JS environment including node, deno, bun, edge runtime, and cloudflare worker",
-  "version": "0.1.19",
+  "version": "0.1.20",
   "type": "module",
   "types": "dist/index.d.ts",
   "module": "dist/index.js",
@@ -124,7 +124,7 @@
   "devDependencies": {
     "@types/node": "^22.9.0",
     "@types/readable-stream": "^4.0.15",
-    "@xenova/transformers": "^2.17.2",
+    "@huggingface/transformers": "^3.0.2",
     "bunchee": "5.6.1",
     "gpt-tokenizer": "^2.6.0",
     "pathe": "^1.1.2",
@@ -132,7 +132,7 @@
   },
   "peerDependencies": {
     "@aws-crypto/sha256-js": "^5.2.0",
-    "@xenova/transformers": "^2.17.2",
+    "@huggingface/transformers": "^3.0.2",
     "gpt-tokenizer": "^2.5.0",
     "js-tiktoken": "^1.0.12",
     "pathe": "^1.1.2"
@@ -141,7 +141,7 @@
     "@aws-crypto/sha256-js": {
       "optional": true
     },
-    "@xenova/transformers": {
+    "@huggingface/transformers": {
       "optional": true
     },
     "pathe": {

packages/env/src/internal/multi-model/browser.ts

@@ -8,8 +8,10 @@ export {
 export async function loadTransformers(onLoad: OnLoad) {
   if (getTransformers() === null) {
     setTransformers(
-      // @ts-expect-error no type
-      await import("https://cdn.jsdelivr.net/npm/@xenova/transformers@2.17.2"),
+      await import(
+        // @ts-expect-error no type
+        "https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.0.2"
+      ),
     );
   } else {
     return getTransformers()!;

packages/env/src/internal/multi-model/node.ts

@@ -8,7 +8,7 @@ export {
 
 export async function loadTransformers(onLoad: OnLoad) {
   if (getTransformers() === null) {
-    setTransformers(await import("@xenova/transformers"));
+    setTransformers(await import("@huggingface/transformers"));
   } else {
     return getTransformers()!;
   }

packages/env/src/internal/multi-model/non-node.ts

@@ -9,7 +9,7 @@ export async function loadTransformers(onLoad: OnLoad) {
   if (getTransformers() === null) {
     /**
      * If you see this warning, it means that the current environment does not support the transformer.
-     *  because "@xeonva/transformers" highly depends on Node.js APIs.
+     *  because "@huggingface/transformers" highly depends on Node.js APIs.
      *
      * One possible solution is to fix their implementation to make it work in the non-Node.js environment,
      *  but it's not worth the effort because Edge Runtime and Cloudflare Workers are not the for heavy Machine Learning task.
@@ -17,14 +17,14 @@ export async function loadTransformers(onLoad: OnLoad) {
      * Or you can provide an RPC server that runs the transformer in a Node.js environment.
      * Or you just run the code in a Node.js environment.
      *
-     * Refs: https://github.com/xenova/transformers.js/issues/309
+     * Refs: https://github.com/huggingface/transformers.js/issues/309
      */
     console.warn(
-      '"@xenova/transformers" is not officially supported in this environment, some features may not work as expected.',
+      '"@huggingface/transformers" is not officially supported in this environment, some features may not work as expected.',
     );
     setTransformers(
       // @ts-expect-error no type
-      await import("@xenova/transformers/dist/transformers"),
+      await import("@huggingface/transformers/dist/transformers.js"),
     );
   } else {
     return getTransformers()!;

packages/env/src/internal/multi-model/shared.ts

@@ -1,17 +1,17 @@
-let transformer: typeof import("@xenova/transformers") | null = null;
+let transformer: typeof import("@huggingface/transformers") | null = null;
 
 export function getTransformers() {
   return transformer;
 }
 
-export function setTransformers(t: typeof import("@xenova/transformers")) {
+export function setTransformers(t: typeof import("@huggingface/transformers")) {
   transformer = t;
 }
 
 export type OnLoad = (
-  transformer: typeof import("@xenova/transformers"),
+  transformer: typeof import("@huggingface/transformers"),
 ) => void;
 
 export type LoadTransformerEvent = {
-  transformer: typeof import("@xenova/transformers");
+  transformer: typeof import("@huggingface/transformers");
 };

packages/experimental/CHANGELOG.md

@@ -1,5 +1,32 @@
 # @llamaindex/experimental
 
+## 0.0.124
+
+### Patch Changes
+
+- llamaindex@0.8.12
+
+## 0.0.123
+
+### Patch Changes
+
+- llamaindex@0.8.11
+
+## 0.0.122
+
+### Patch Changes
+
+- Updated dependencies [f066e50]
+  - llamaindex@0.8.10
+
+## 0.0.121
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - llamaindex@0.8.9
+
 ## 0.0.120
 
 ### Patch Changes

packages/experimental/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/experimental",
   "description": "Experimental package for LlamaIndexTS",
-  "version": "0.0.120",
+  "version": "0.0.124",
   "type": "module",
   "types": "dist/type/index.d.ts",
   "main": "dist/cjs/index.js",

packages/llamaindex/CHANGELOG.md

@@ -1,5 +1,97 @@
 # llamaindex
 
+## 0.8.12
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+  - @llamaindex/cloud@2.0.9
+  - @llamaindex/node-parser@0.0.10
+  - @llamaindex/anthropic@0.0.18
+  - @llamaindex/clip@0.0.18
+  - @llamaindex/deepinfra@0.0.18
+  - @llamaindex/huggingface@0.0.18
+  - @llamaindex/ollama@0.0.25
+  - @llamaindex/portkey-ai@0.0.18
+  - @llamaindex/replicate@0.0.18
+  - @llamaindex/readers@1.0.10
+  - @llamaindex/groq@0.0.33
+  - @llamaindex/vllm@0.0.4
+
+## 0.8.11
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+  - @llamaindex/cloud@2.0.8
+  - @llamaindex/node-parser@0.0.9
+  - @llamaindex/anthropic@0.0.17
+  - @llamaindex/clip@0.0.17
+  - @llamaindex/deepinfra@0.0.17
+  - @llamaindex/huggingface@0.0.17
+  - @llamaindex/ollama@0.0.24
+  - @llamaindex/openai@0.1.33
+  - @llamaindex/portkey-ai@0.0.17
+  - @llamaindex/replicate@0.0.17
+  - @llamaindex/readers@1.0.9
+  - @llamaindex/groq@0.0.32
+  - @llamaindex/vllm@0.0.3
+
+## 0.8.10
+
+### Patch Changes
+
+- f066e50: feat: vllm support
+- Updated dependencies [f066e50]
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+  - @llamaindex/vllm@0.0.2
+  - @llamaindex/core@0.4.7
+  - @llamaindex/cloud@2.0.7
+  - @llamaindex/node-parser@0.0.8
+  - @llamaindex/anthropic@0.0.16
+  - @llamaindex/clip@0.0.16
+  - @llamaindex/deepinfra@0.0.16
+  - @llamaindex/huggingface@0.0.16
+  - @llamaindex/ollama@0.0.23
+  - @llamaindex/openai@0.1.32
+  - @llamaindex/portkey-ai@0.0.16
+  - @llamaindex/replicate@0.0.16
+  - @llamaindex/readers@1.0.8
+  - @llamaindex/groq@0.0.31
+
+## 0.8.9
+
+### Patch Changes
+
+- 4fc001c: chore: bump `@huggingface/transformers`
+
+  Upgrade to v3, please read https://github.com/huggingface/transformers.js/releases/tag/3.0.0 for more information.
+
+- 4d4cd8a: feat: support ollama tool call
+
+  Note that `OllamaEmbedding` now is not the subclass of `Ollama`.
+
+- Updated dependencies [4fc001c]
+- Updated dependencies [4d4cd8a]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/clip@0.0.15
+  - @llamaindex/huggingface@0.0.15
+  - @llamaindex/ollama@0.0.22
+  - @llamaindex/cloud@2.0.6
+  - @llamaindex/core@0.4.6
+  - @llamaindex/node-parser@0.0.7
+  - @llamaindex/anthropic@0.0.15
+  - @llamaindex/deepinfra@0.0.15
+  - @llamaindex/groq@0.0.30
+  - @llamaindex/openai@0.1.31
+  - @llamaindex/portkey-ai@0.0.15
+  - @llamaindex/replicate@0.0.15
+  - @llamaindex/readers@1.0.7
+
 ## 0.8.8
 
 ### Patch Changes

packages/llamaindex/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llamaindex",
-  "version": "0.8.8",
+  "version": "0.8.12",
   "license": "MIT",
   "type": "module",
   "keywords": [
@@ -29,7 +29,7 @@
     "@discoveryjs/json-ext": "^0.6.1",
     "@google-cloud/vertexai": "1.2.0",
     "@google/generative-ai": "0.12.0",
-    "@grpc/grpc-js": "^1.11.1",
+    "@grpc/grpc-js": "^1.12.2",
     "@llamaindex/anthropic": "workspace:*",
     "@llamaindex/clip": "workspace:*",
     "@llamaindex/cloud": "workspace:*",
@@ -44,6 +44,7 @@
     "@llamaindex/portkey-ai": "workspace:*",
     "@llamaindex/readers": "workspace:*",
     "@llamaindex/replicate": "workspace:*",
+    "@llamaindex/vllm": "workspace:*",
     "@mistralai/mistralai": "^1.0.4",
     "@mixedbread-ai/sdk": "^2.2.11",
     "@pinecone-database/pinecone": "^3.0.2",
@@ -85,10 +86,10 @@
     }
   },
   "devDependencies": {
+    "@huggingface/transformers": "^3.0.2",
     "@swc/cli": "^0.5.0",
     "@swc/core": "^1.7.22",
     "@vercel/postgres": "^0.10.0",
-    "@xenova/transformers": "^2.17.2",
     "concurrently": "^9.1.0",
     "glob": "^11.0.0",
     "pg": "^8.12.0",

packages/llamaindex/src/agent/index.ts

@@ -1,4 +1,9 @@
 export * from "@llamaindex/core/agent";
+export {
+  OllamaAgent,
+  OllamaAgentWorker,
+  type OllamaAgentParams,
+} from "@llamaindex/ollama";
 export {
   AnthropicAgent,
   AnthropicAgentWorker,
@@ -16,7 +21,6 @@ export {
   ReActAgent,
   type ReACTAgentParams,
 } from "./react.js";
-
 // todo: ParallelAgent
 // todo: CustomAgent
 // todo: ReactMultiModal

packages/llamaindex/src/embeddings/OllamaEmbedding.ts

@@ -1,7 +1 @@
-import type { BaseEmbedding } from "@llamaindex/core/embeddings";
-import { Ollama } from "@llamaindex/ollama";
-
-/**
- * OllamaEmbedding is an alias for Ollama that implements the BaseEmbedding interface.
- */
-export class OllamaEmbedding extends Ollama implements BaseEmbedding {}
+export { OllamaEmbedding } from "@llamaindex/ollama";

packages/llamaindex/src/llm/index.ts

@@ -1,3 +1,4 @@
+export { VLLM, type VLLMParams } from "@llamaindex/vllm";
 export {
   ALL_AVAILABLE_ANTHROPIC_LEGACY_MODELS,
   ALL_AVAILABLE_ANTHROPIC_MODELS,
@@ -6,7 +7,6 @@ export {
 } from "./anthropic.js";
 export { FireworksLLM } from "./fireworks.js";
 export { Gemini, GeminiSession } from "./gemini/base.js";
-
 export {
   GEMINI_MODEL,
   type GoogleGeminiSessionOptions,

packages/llamaindex/src/next.ts

@@ -22,7 +22,7 @@ export default function withLlamaIndex(config: any) {
   config.experimental.serverComponentsExternalPackages =
     config.experimental.serverComponentsExternalPackages ?? [];
   config.experimental.serverComponentsExternalPackages.push(
-    "@xenova/transformers",
+    "@huggingface/transformers",
   );
   const userWebpack = config.webpack;
   // eslint-disable-next-line @typescript-eslint/no-explicit-any

packages/node-parser/CHANGELOG.md

@@ -1,5 +1,35 @@
 # @llamaindex/node-parser
 
+## 0.0.10
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
+## 0.0.9
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+
+## 0.0.8
+
+### Patch Changes
+
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+  - @llamaindex/core@0.4.7
+
+## 0.0.7
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/core@0.4.6
+
 ## 0.0.6
 
 ### Patch Changes

packages/node-parser/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@llamaindex/node-parser",
-  "version": "0.0.6",
+  "version": "0.0.10",
   "description": "Node parser for LlamaIndex",
   "type": "module",
   "exports": {

packages/providers/anthropic/CHANGELOG.md

@@ -1,5 +1,35 @@
 # @llamaindex/anthropic
 
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+
+## 0.0.17
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+
+## 0.0.16
+
+### Patch Changes
+
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+  - @llamaindex/core@0.4.7
+
+## 0.0.15
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/core@0.4.6
+
 ## 0.0.14
 
 ### Patch Changes

packages/providers/anthropic/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/anthropic",
   "description": "Anthropic Adapter for LlamaIndex",
-  "version": "0.0.14",
+  "version": "0.0.18",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/anthropic/src/agent.ts

@@ -11,7 +11,7 @@ import { Settings } from "@llamaindex/core/global";
 import type { EngineResponse } from "@llamaindex/core/schema";
 import { Anthropic } from "./llm.js";
 
-export type AnthropicAgentParams = LLMAgentParams;
+export type AnthropicAgentParams = LLMAgentParams<Anthropic>;
 
 export class AnthropicAgentWorker extends LLMAgentWorker {}
 

packages/providers/clip/CHANGELOG.md

@@ -1,5 +1,43 @@
 # @llamaindex/clip
 
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+
+## 0.0.17
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+  - @llamaindex/openai@0.1.33
+
+## 0.0.16
+
+### Patch Changes
+
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+  - @llamaindex/core@0.4.7
+  - @llamaindex/openai@0.1.32
+
+## 0.0.15
+
+### Patch Changes
+
+- 4fc001c: chore: bump `@huggingface/transformers`
+
+  Upgrade to v3, please read https://github.com/huggingface/transformers.js/releases/tag/3.0.0 for more information.
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/core@0.4.6
+  - @llamaindex/openai@0.1.31
+
 ## 0.0.14
 
 ### Patch Changes

packages/providers/clip/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/clip",
   "description": "Clip Embedding Adapter for LlamaIndex",
-  "version": "0.0.14",
+  "version": "0.0.18",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",
@@ -45,6 +45,9 @@
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
     "@llamaindex/openai": "workspace:*",
-    "@xenova/transformers": "^2.17.2"
+    "@huggingface/transformers": "^3.0.2"
+  },
+  "peerDependencies": {
+    "@huggingface/transformers": "^3.0.2"
   }
 }

packages/providers/clip/src/embedding.ts

@@ -1,17 +1,17 @@
 import { MultiModalEmbedding } from "@llamaindex/core/embeddings";
 import type { ImageType } from "@llamaindex/core/schema";
 // only import type, to avoid bundling error
-import { Settings } from "@llamaindex/core/global";
-import {
-  type LoadTransformerEvent,
-  loadTransformers,
-} from "@llamaindex/env/multi-model";
 import type {
   CLIPTextModelWithProjection,
   CLIPVisionModelWithProjection,
   PreTrainedTokenizer,
   Processor,
-} from "@xenova/transformers";
+} from "@huggingface/transformers";
+import { Settings } from "@llamaindex/core/global";
+import {
+  type LoadTransformerEvent,
+  loadTransformers,
+} from "@llamaindex/env/multi-model";
 import { ClipEmbeddingModelType } from "./shared";
 
 declare module "@llamaindex/core/global" {

packages/providers/deepinfra/CHANGELOG.md

@@ -1,5 +1,39 @@
 # @llamaindex/deepinfra
 
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+
+## 0.0.17
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+  - @llamaindex/openai@0.1.33
+
+## 0.0.16
+
+### Patch Changes
+
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+  - @llamaindex/core@0.4.7
+  - @llamaindex/openai@0.1.32
+
+## 0.0.15
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/core@0.4.6
+  - @llamaindex/openai@0.1.31
+
 ## 0.0.14
 
 ### Patch Changes

packages/providers/deepinfra/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/deepinfra",
   "description": "Deepinfra Adapter for LlamaIndex",
-  "version": "0.0.14",
+  "version": "0.0.18",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/groq/CHANGELOG.md

@@ -1,5 +1,32 @@
 # @llamaindex/groq
 
+## 0.0.33
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/openai@0.1.34
+
+## 0.0.32
+
+### Patch Changes
+
+- @llamaindex/openai@0.1.33
+
+## 0.0.31
+
+### Patch Changes
+
+- @llamaindex/openai@0.1.32
+
+## 0.0.30
+
+### Patch Changes
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/openai@0.1.31
+
 ## 0.0.29
 
 ### Patch Changes

packages/providers/groq/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/groq",
   "description": "Groq Adapter for LlamaIndex",
-  "version": "0.0.29",
+  "version": "0.0.33",
   "type": "module",
   "main": "./dist/index.cjs",
   "module": "./dist/index.js",

packages/providers/huggingface/CHANGELOG.md

@@ -1,5 +1,43 @@
 # @llamaindex/huggingface
 
+## 0.0.18
+
+### Patch Changes
+
+- Updated dependencies [7ae6eaa]
+  - @llamaindex/core@0.4.9
+  - @llamaindex/openai@0.1.34
+
+## 0.0.17
+
+### Patch Changes
+
+- Updated dependencies [f865c98]
+  - @llamaindex/core@0.4.8
+  - @llamaindex/openai@0.1.33
+
+## 0.0.16
+
+### Patch Changes
+
+- Updated dependencies [d89ebe0]
+- Updated dependencies [fd8c882]
+  - @llamaindex/core@0.4.7
+  - @llamaindex/openai@0.1.32
+
+## 0.0.15
+
+### Patch Changes
+
+- 4fc001c: chore: bump `@huggingface/transformers`
+
+  Upgrade to v3, please read https://github.com/huggingface/transformers.js/releases/tag/3.0.0 for more information.
+
+- Updated dependencies [4fc001c]
+  - @llamaindex/env@0.1.20
+  - @llamaindex/core@0.4.6
+  - @llamaindex/openai@0.1.31
+
 ## 0.0.14
 
 ### Patch Changes

packages/providers/huggingface/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@llamaindex/huggingface",
   "description": "Huggingface Adapter for LlamaIndex",
-  "version": "0.0.14",
+  "version": "0.0.18",
   "type": "module",
   "types": "dist/index.d.ts",
   "main": "dist/index.cjs",
@@ -46,6 +46,9 @@
     "@llamaindex/core": "workspace:*",
     "@llamaindex/env": "workspace:*",
     "@llamaindex/openai": "workspace:*",
-    "@xenova/transformers": "^2.17.2"
+    "@huggingface/transformers": "^3.0.2"
+  },
+  "peerDependencies": {
+    "@huggingface/transformers": "^3.0.2"
   }
 }

packages/providers/huggingface/src/embedding.ts

@@ -1,10 +1,10 @@
+import type { pipeline } from "@huggingface/transformers";
 import { BaseEmbedding } from "@llamaindex/core/embeddings";
 import { Settings } from "@llamaindex/core/global";
 import {
   type LoadTransformerEvent,
   loadTransformers,
 } from "@llamaindex/env/multi-model";
-import type { pipeline } from "@xenova/transformers";
 import { HuggingFaceEmbeddingModelType } from "./shared";
 
 declare module "@llamaindex/core/global" {
@@ -13,6 +13,11 @@ declare module "@llamaindex/core/global" {
   }
 }
 
+export type HuggingFaceEmbeddingParams = {
+  modelType?: string;
+  modelOptions?: Parameters<typeof pipeline<"feature-extraction">>[2];
+};
+
 /**
  * Uses feature extraction from '@xenova/transformers' to generate embeddings.
  * Per default the model [XENOVA_ALL_MINILM_L6_V2](https://huggingface.co/Xenova/all-MiniLM-L6-v2) is used.
@@ -28,15 +33,20 @@ declare module "@llamaindex/core/global" {
  */
 export class HuggingFaceEmbedding extends BaseEmbedding {
   modelType: string = HuggingFaceEmbeddingModelType.XENOVA_ALL_MINILM_L6_V2;
-  quantized: boolean = true;
+  modelOptions: Parameters<typeof pipeline<"feature-extraction">>[2] = {};
 
   private extractor: Awaited<
     ReturnType<typeof pipeline<"feature-extraction">>
   > | null = null;
 
-  constructor(init?: Partial<HuggingFaceEmbedding>) {
+  constructor(params: HuggingFaceEmbeddingParams = {}) {
     super();
-    Object.assign(this, init);
+    if (params.modelType) {
+      this.modelType = params.modelType;
+    }
+    if (params.modelOptions) {
+      this.modelOptions = params.modelOptions;
+    }
   }
 
   async getExtractor() {
@@ -50,9 +60,11 @@ export class HuggingFaceEmbedding extends BaseEmbedding {
           true,
         );
       });
-      this.extractor = await pipeline("feature-extraction", this.modelType, {
-        quantized: this.quantized,
-      });
+      this.extractor = await pipeline(
+        "feature-extraction",
+        this.modelType,
+        this.modelOptions,
+      );
     }
     return this.extractor;
   }

packages/providers/huggingface/src/index.ts

@@ -1,4 +1,7 @@
-export { HuggingFaceEmbedding } from "./embedding";
+export {
+  HuggingFaceEmbedding,
+  type HuggingFaceEmbeddingParams,
+} from "./embedding";
 export { HuggingFaceLLM, type HFLLMConfig } from "./llm";
 export {
   HuggingFaceEmbeddingModelType,

packages/providers/huggingface/src/llm.ts

@@ -1,3 +1,8 @@
+import type {
+  PreTrainedModel,
+  PreTrainedTokenizer,
+  Tensor,
+} from "@huggingface/transformers";
 import { wrapLLMEvent } from "@llamaindex/core/decorator";
 import { Settings } from "@llamaindex/core/global";
 import "@llamaindex/core/llms";
@@ -10,11 +15,6 @@ import {
   type LLMMetadata,
 } from "@llamaindex/core/llms";
 import { loadTransformers } from "@llamaindex/env/multi-model";
-import type {
-  PreTrainedModel,
-  PreTrainedTokenizer,
-  Tensor,
-} from "@xenova/transformers";
 import { DEFAULT_PARAMS } from "./shared";
 
 const DEFAULT_HUGGINGFACE_MODEL = "stabilityai/stablelm-tuned-alpha-3b";
@@ -122,7 +122,10 @@ export class HuggingFaceLLM extends BaseLLM {
     // TODO: the input for model.generate should be updated when using @xenova/transformers v3
     // We should add `stopping_criteria` also when it's supported in v3
     // See: https://github.com/xenova/transformers.js/blob/3260640b192b3e06a10a1f4dc004b1254fdf1b80/src/models.js#L1248C9-L1248C27
-    const outputs = await model.generate(inputs, this.metadata);
+    const outputs = (await model.generate({
+      inputs,
+      ...this.metadata,
+    })) as Tensor;
     const outputText = tokenizer.batch_decode(outputs, {
       skip_special_tokens: false,
     });