@tanstack/ai-angular 0.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md ADDED
@@ -0,0 +1,158 @@
1
+ <div align="center">
2
+ <img src="https://raw.githubusercontent.com/TanStack/ai/main/media/header_ai.png" alt="TanStack AI" />
3
+ </div>
4
+
5
+ <br />
6
+
7
+ <div align="center">
8
+ <a href="https://npmjs.com/package/@tanstack/ai-angular" target="_parent">
9
+ <img alt="NPM downloads" src="https://img.shields.io/npm/dm/@tanstack/ai-angular.svg" />
10
+ </a>
11
+ <a href="https://github.com/TanStack/ai" target="_parent">
12
+ <img alt="GitHub stars" src="https://img.shields.io/github/stars/TanStack/ai.svg?style=social&label=Star" />
13
+ </a>
14
+ <a href="https://github.com/TanStack/ai/releases" target="_parent">
15
+ <img alt="Release" src="https://img.shields.io/github/v/release/tanstack/ai" />
16
+ </a>
17
+ <a href="https://bundlephobia.com/result?p=@tanstack/ai-angular@latest" target="_parent">
18
+ <img alt="Bundle size" src="https://badgen.net/bundlephobia/minzip/@tanstack/ai-angular@latest" />
19
+ </a>
20
+ <a href="https://twitter.com/tan_stack">
21
+ <img alt="Follow @TanStack" src="https://img.shields.io/twitter/follow/tan_stack.svg?style=social" />
22
+ </a>
23
+ </div>
24
+
25
+ # TanStack AI — Angular
26
+
27
+ Angular signal-based bindings for TanStack AI — streaming chat, tool-calling agents, and media generation built on Angular's native reactivity model.
28
+
29
+ ## <a href="https://tanstack.com/ai">Read the docs -></a>
30
+
31
+ ## Install
32
+
33
+ ```bash
34
+ pnpm add @tanstack/ai-angular @tanstack/ai
35
+ ```
36
+
37
+ ```bash
38
+ npm install @tanstack/ai-angular @tanstack/ai
39
+ ```
40
+
41
+ ## Minimal Usage
42
+
43
+ > **Important:** All `inject*` functions use Angular's dependency injection system and **must** be called within an Angular injection context — a component or directive class field initializer, the constructor, or inside `runInInjectionContext`. Calling them outside an injection context will throw a runtime error.
44
+
45
+ The example below shows a standalone component that streams chat messages from a server endpoint via SSE:
46
+
47
+ ```typescript
48
+ import { Component } from '@angular/core'
49
+ import { CommonModule } from '@angular/common'
50
+ import { injectChat } from '@tanstack/ai-angular'
51
+ import { fetchServerSentEvents } from '@tanstack/ai-client'
52
+
53
+ @Component({
54
+ selector: 'app-chat',
55
+ standalone: true,
56
+ imports: [CommonModule],
57
+ template: `
58
+ <ul>
59
+ @for (message of chat.messages(); track message.id) {
60
+ <li>{{ message.role }}: {{ message.content }}</li>
61
+ }
62
+ </ul>
63
+ <input #input placeholder="Type a message..." />
64
+ <button (click)="chat.sendMessage(input.value); input.value = ''">
65
+ Send
66
+ </button>
67
+ @if (chat.isLoading()) {
68
+ <p>Thinking...</p>
69
+ }
70
+ `,
71
+ })
72
+ export class ChatComponent {
73
+ // injectChat is called in a field initializer — this is a valid injection context.
74
+ chat = injectChat({
75
+ connection: fetchServerSentEvents('/api/chat'),
76
+ })
77
+ }
78
+ ```
79
+
80
+ All state is exposed as Angular `Signal`s. Read them by calling them as functions:
81
+
82
+ | Signal | Type | Description |
83
+ | ------------------------- | -------------------- | ------------------------------------------- |
84
+ | `chat.messages()` | `UIMessage[]` | Current message list |
85
+ | `chat.isLoading()` | `boolean` | Whether a response is streaming |
86
+ | `chat.error()` | `Error \| undefined` | Last error, if any |
87
+ | `chat.status()` | `ChatClientState` | `'ready'`, `'streaming'`, `'error'`, ... |
88
+ | `chat.isSubscribed()` | `boolean` | Whether a live (SSE push) session is active |
89
+ | `chat.connectionStatus()` | `ConnectionStatus` | Transport connection status |
90
+
91
+ Available methods on the return value: `sendMessage`, `append`, `reload`, `stop`, `clear`, `setMessages`, `addToolResult`, `addToolApprovalResponse`.
92
+
93
+ ## Server endpoint
94
+
95
+ The client pairs with any endpoint that returns a TanStack AI SSE stream:
96
+
97
+ ```typescript
98
+ import { chat, toServerSentEventsResponse } from '@tanstack/ai'
99
+ import { openaiText } from '@tanstack/ai-openai'
100
+
101
+ export async function POST(request: Request) {
102
+ const body = await request.json()
103
+
104
+ const stream = chat({
105
+ adapter: openaiText('gpt-5.5'),
106
+ messages: body.messages,
107
+ })
108
+
109
+ return toServerSentEventsResponse(stream)
110
+ }
111
+ ```
112
+
113
+ ## Available Functions
114
+
115
+ | Function | Description |
116
+ | ---------------------- | ---------------------------------------------------------------- |
117
+ | `injectChat` | Streaming chat with messages, tool calls, and structured outputs |
118
+ | `injectGeneration` | Generic generation client (streaming or one-shot) |
119
+ | `injectGenerateImage` | Image generation |
120
+ | `injectGenerateAudio` | Audio generation |
121
+ | `injectGenerateVideo` | Video generation |
122
+ | `injectGenerateSpeech` | Text-to-speech |
123
+ | `injectSummarize` | Summarization |
124
+ | `injectTranscription` | Audio transcription |
125
+
126
+ All generation functions return signals (`result`, `isLoading`, `error`, `status`) and methods (`generate`, `stop`, `reset`).
127
+
128
+ ## Injection Context
129
+
130
+ Angular's DI system requires that `inject()` is called during component construction. Every `inject*` function in this package calls `inject()` internally. Valid call sites:
131
+
132
+ ```typescript
133
+ // Field initializer (recommended)
134
+ export class MyComponent {
135
+ chat = injectChat({ connection: fetchServerSentEvents('/api/chat') })
136
+ }
137
+
138
+ // Constructor
139
+ export class MyComponent {
140
+ chat: ReturnType<typeof injectChat>
141
+ constructor() {
142
+ this.chat = injectChat({ connection: fetchServerSentEvents('/api/chat') })
143
+ }
144
+ }
145
+
146
+ // Inside runInInjectionContext
147
+ const chat = runInInjectionContext(injector, () =>
148
+ injectChat({ connection: fetchServerSentEvents('/api/chat') }),
149
+ )
150
+ ```
151
+
152
+ ## Get Involved
153
+
154
+ - Read the [docs](https://tanstack.com/ai).
155
+ - Participate in [GitHub discussions](https://github.com/TanStack/ai/discussions).
156
+ - Chat with the community on [Discord](https://discord.com/invite/WrRKjPJ).
157
+ - See [CONTRIBUTING.md](https://github.com/TanStack/ai/blob/main/CONTRIBUTING.md) for setup instructions.
158
+ - [Become a sponsor](https://github.com/sponsors/tannerlinsley/).
package/dist/README.md ADDED
@@ -0,0 +1,158 @@
1
+ <div align="center">
2
+ <img src="https://raw.githubusercontent.com/TanStack/ai/main/media/header_ai.png" alt="TanStack AI" />
3
+ </div>
4
+
5
+ <br />
6
+
7
+ <div align="center">
8
+ <a href="https://npmjs.com/package/@tanstack/ai-angular" target="_parent">
9
+ <img alt="NPM downloads" src="https://img.shields.io/npm/dm/@tanstack/ai-angular.svg" />
10
+ </a>
11
+ <a href="https://github.com/TanStack/ai" target="_parent">
12
+ <img alt="GitHub stars" src="https://img.shields.io/github/stars/TanStack/ai.svg?style=social&label=Star" />
13
+ </a>
14
+ <a href="https://github.com/TanStack/ai/releases" target="_parent">
15
+ <img alt="Release" src="https://img.shields.io/github/v/release/tanstack/ai" />
16
+ </a>
17
+ <a href="https://bundlephobia.com/result?p=@tanstack/ai-angular@latest" target="_parent">
18
+ <img alt="Bundle size" src="https://badgen.net/bundlephobia/minzip/@tanstack/ai-angular@latest" />
19
+ </a>
20
+ <a href="https://twitter.com/tan_stack">
21
+ <img alt="Follow @TanStack" src="https://img.shields.io/twitter/follow/tan_stack.svg?style=social" />
22
+ </a>
23
+ </div>
24
+
25
+ # TanStack AI — Angular
26
+
27
+ Angular signal-based bindings for TanStack AI — streaming chat, tool-calling agents, and media generation built on Angular's native reactivity model.
28
+
29
+ ## <a href="https://tanstack.com/ai">Read the docs -></a>
30
+
31
+ ## Install
32
+
33
+ ```bash
34
+ pnpm add @tanstack/ai-angular @tanstack/ai
35
+ ```
36
+
37
+ ```bash
38
+ npm install @tanstack/ai-angular @tanstack/ai
39
+ ```
40
+
41
+ ## Minimal Usage
42
+
43
+ > **Important:** All `inject*` functions use Angular's dependency injection system and **must** be called within an Angular injection context — a component or directive class field initializer, the constructor, or inside `runInInjectionContext`. Calling them outside an injection context will throw a runtime error.
44
+
45
+ The example below shows a standalone component that streams chat messages from a server endpoint via SSE:
46
+
47
+ ```typescript
48
+ import { Component } from '@angular/core'
49
+ import { CommonModule } from '@angular/common'
50
+ import { injectChat } from '@tanstack/ai-angular'
51
+ import { fetchServerSentEvents } from '@tanstack/ai-client'
52
+
53
+ @Component({
54
+ selector: 'app-chat',
55
+ standalone: true,
56
+ imports: [CommonModule],
57
+ template: `
58
+ <ul>
59
+ @for (message of chat.messages(); track message.id) {
60
+ <li>{{ message.role }}: {{ message.content }}</li>
61
+ }
62
+ </ul>
63
+ <input #input placeholder="Type a message..." />
64
+ <button (click)="chat.sendMessage(input.value); input.value = ''">
65
+ Send
66
+ </button>
67
+ @if (chat.isLoading()) {
68
+ <p>Thinking...</p>
69
+ }
70
+ `,
71
+ })
72
+ export class ChatComponent {
73
+ // injectChat is called in a field initializer — this is a valid injection context.
74
+ chat = injectChat({
75
+ connection: fetchServerSentEvents('/api/chat'),
76
+ })
77
+ }
78
+ ```
79
+
80
+ All state is exposed as Angular `Signal`s. Read them by calling them as functions:
81
+
82
+ | Signal | Type | Description |
83
+ | ------------------------- | -------------------- | ------------------------------------------- |
84
+ | `chat.messages()` | `UIMessage[]` | Current message list |
85
+ | `chat.isLoading()` | `boolean` | Whether a response is streaming |
86
+ | `chat.error()` | `Error \| undefined` | Last error, if any |
87
+ | `chat.status()` | `ChatClientState` | `'ready'`, `'streaming'`, `'error'`, ... |
88
+ | `chat.isSubscribed()` | `boolean` | Whether a live (SSE push) session is active |
89
+ | `chat.connectionStatus()` | `ConnectionStatus` | Transport connection status |
90
+
91
+ Available methods on the return value: `sendMessage`, `append`, `reload`, `stop`, `clear`, `setMessages`, `addToolResult`, `addToolApprovalResponse`.
92
+
93
+ ## Server endpoint
94
+
95
+ The client pairs with any endpoint that returns a TanStack AI SSE stream:
96
+
97
+ ```typescript
98
+ import { chat, toServerSentEventsResponse } from '@tanstack/ai'
99
+ import { openaiText } from '@tanstack/ai-openai'
100
+
101
+ export async function POST(request: Request) {
102
+ const body = await request.json()
103
+
104
+ const stream = chat({
105
+ adapter: openaiText('gpt-5.5'),
106
+ messages: body.messages,
107
+ })
108
+
109
+ return toServerSentEventsResponse(stream)
110
+ }
111
+ ```
112
+
113
+ ## Available Functions
114
+
115
+ | Function | Description |
116
+ | ---------------------- | ---------------------------------------------------------------- |
117
+ | `injectChat` | Streaming chat with messages, tool calls, and structured outputs |
118
+ | `injectGeneration` | Generic generation client (streaming or one-shot) |
119
+ | `injectGenerateImage` | Image generation |
120
+ | `injectGenerateAudio` | Audio generation |
121
+ | `injectGenerateVideo` | Video generation |
122
+ | `injectGenerateSpeech` | Text-to-speech |
123
+ | `injectSummarize` | Summarization |
124
+ | `injectTranscription` | Audio transcription |
125
+
126
+ All generation functions return signals (`result`, `isLoading`, `error`, `status`) and methods (`generate`, `stop`, `reset`).
127
+
128
+ ## Injection Context
129
+
130
+ Angular's DI system requires that `inject()` is called during component construction. Every `inject*` function in this package calls `inject()` internally. Valid call sites:
131
+
132
+ ```typescript
133
+ // Field initializer (recommended)
134
+ export class MyComponent {
135
+ chat = injectChat({ connection: fetchServerSentEvents('/api/chat') })
136
+ }
137
+
138
+ // Constructor
139
+ export class MyComponent {
140
+ chat: ReturnType<typeof injectChat>
141
+ constructor() {
142
+ this.chat = injectChat({ connection: fetchServerSentEvents('/api/chat') })
143
+ }
144
+ }
145
+
146
+ // Inside runInInjectionContext
147
+ const chat = runInInjectionContext(injector, () =>
148
+ injectChat({ connection: fetchServerSentEvents('/api/chat') }),
149
+ )
150
+ ```
151
+
152
+ ## Get Involved
153
+
154
+ - Read the [docs](https://tanstack.com/ai).
155
+ - Participate in [GitHub discussions](https://github.com/TanStack/ai/discussions).
156
+ - Chat with the community on [Discord](https://discord.com/invite/WrRKjPJ).
157
+ - See [CONTRIBUTING.md](https://github.com/TanStack/ai/blob/main/CONTRIBUTING.md) for setup instructions.
158
+ - [Become a sponsor](https://github.com/sponsors/tannerlinsley/).