@picahq/toolkit 0.14.0 → 1.0.0

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.
Files changed (2) hide show
  1. package/README.md +15 -3
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -6,6 +6,13 @@
6
6
 
7
7
  Pica's ToolKit provides enterprise-grade integration capabilities for AI agents built with the Vercel AI SDK. Through Pica's integration layer, agents can seamlessly interact with third-party services and APIs while maintaining enterprise security, compliance, and reliability standards.
8
8
 
9
+ ## Prerequisites
10
+
11
+ Before installing ToolKit, you'll need:
12
+ - **Pica Account** - Sign up for a free account [here](https://app.picaos.com)
13
+ - **Vercel AI SDK** - Version 5.0.0 or higher
14
+ - **LLM Provider & API Key** – You'll need an API key from your preferred LLM provider. Supported providers include: OpenAI, Anthropic, Google, xAI, Groq, Mistral, Cohere, and [many more](https://ai-sdk.dev/providers/ai-sdk-providers).
15
+
9
16
  ## Installation
10
17
 
11
18
  ```bash
@@ -21,7 +28,7 @@ npm install @picahq/toolkit
21
28
 
22
29
  ## Usage
23
30
 
24
- The Pica ToolKit seamlessly integrates with [Vercel AI SDK](https://ai-sdk.dev/docs/introduction), enabling powerful AI capabilities in your applications. Below is a simple example showing how to implement it in a Vercel Agent with read-only permissions on a Gmail connection.
31
+ The Pica ToolKit seamlessly integrates with [Vercel AI SDK](https://ai-sdk.dev/docs/introduction), enabling powerful AI capabilities in your applications. Below is a simple example of using Pica ToolKit in a Next.js (or similar Edge Function) API route handler, powering a chat UI with read-only permissions on a Gmail connection.
25
32
 
26
33
  ```typescript
27
34
  import { Pica } from '@picahq/toolkit';
@@ -38,13 +45,14 @@ export async function POST(req: Request) {
38
45
 
39
46
  const pica = new Pica(process.env.PICA_SECRET_KEY!, {
40
47
  connectors: ["test::gmail::default::6faf1d3707f846ef89295c836df71c94"],
48
+ actions: ["*"],
41
49
  permissions: "read"
42
50
  });
43
51
 
44
52
  const systemPrompt = pica.systemPrompt;
45
53
 
46
54
  const result = streamText({
47
- model: openai("gpt-4.1"),
55
+ model: openai("gpt-5"),
48
56
  messages: convertToModelMessages(messages),
49
57
  tools: {
50
58
  ...pica.tools() // Load the Pica ToolKit
@@ -57,7 +65,7 @@ export async function POST(req: Request) {
57
65
  }
58
66
  ```
59
67
 
60
- > ⭐️ Experience the Pica ToolKit's capabilities firsthand through our interactive demo chat application [here](https://github.com/picahq/toolkit-demo)
68
+ > ⭐️ Experience the Pica ToolKit's capabilities firsthand through our interactive chat playground directly in the [Pica dashboard](https://app.picaos.com/connections)
61
69
 
62
70
 
63
71
  ## What can Pica do?
@@ -92,6 +100,10 @@ Here are some powerful examples use cases:
92
100
  - Conduct market research via Tavily/SerpApi integrations
93
101
  - Perform sentiment analysis on support interactions
94
102
 
103
+ ## Documentation
104
+
105
+ For more detailed documentation, please visit our [documentation site](https://docs.picaos.com/toolkit).
106
+
95
107
  ## License
96
108
 
97
109
  This project is licensed under the GPL-3.0 license. See the [LICENSE](LICENSE) file for details.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@picahq/toolkit",
3
- "version": "0.14.0",
3
+ "version": "1.0.0",
4
4
  "description": "Pica tools for the Vercel AI SDK",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",