IMPLEMENTATION
Call this tool
Connect a user's Google PaLM account once, then configure and run Chat from your backend or agent.
import { PipedreamClient } from "@pipedream/sdk"
const pd = new PipedreamClient({
projectId: process.env.PIPEDREAM_PROJECT_ID!,
clientId: process.env.PIPEDREAM_CLIENT_ID!,
clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
projectEnvironment: "production",
})
const result = await pd.actions.run({
id: "google_palm_api-chat",
externalUserId: "{external_user_id}", // any stable ID for this user in your system
configuredProps: {
google_palm_api: { authProvisionId: "apn_xxxxxxx" },
promptText: "Prompt Text",
previousMessages: ["Previous Messages"],
},
})
console.log(result)curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
-H "Content-Type: application/json" \
-H "X-PD-Environment: production" \
-H "Authorization: Bearer {access_token}" \
-d '{
"external_user_id": "{external_user_id}",
"id": "google_palm_api-chat",
"configured_props": {
"google_palm_api": { "authProvisionId": "apn_xxxxxxx" },
"promptText": "Prompt Text",
"previousMessages": ["Previous Messages"]
}
}'// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
new URL("https://remote.mcp.pipedream.net/v3"),
{
requestInit: {
headers: {
Authorization: `Bearer ${accessToken}`,
"x-pd-project-id": "{project_id}",
"x-pd-environment": "production",
"x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
"x-pd-app-slug": "google_palm_api",
},
},
},
)
const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)
const { tools } = await mcp.listTools()
// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
name: "google_palm_api-chat",
arguments: {
promptText: "Prompt Text",
previousMessages: ["Previous Messages"],
},
})SCHEMA
Inputs
Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.
| Property | Type | Description |
|---|---|---|
promptText Prompt Text | string | The text to be used as a prompt for the chat Required |
previousMessages Previous Messages | string[] | The previous messages in the chat. If provided, will override the chat history Optional |
temperature Temperature | string | The temperature to use for the chat. Values can range from [0.0,1.0], inclusive.
A value closer to 1.0 will produce responses that are more varied and creative, while a value closer to 0.0 will typically result in more straightforward responses from the model.
Defaults to 0.5 Optional |
context Context | string | Text that should be provided to the model first, to ground the response Optional |
candidateCount Candidate Count | integer | The maximum number of generated response messages to return. This value must be between [1, 8], inclusive. If unset, this will default to 1. Note: Only unique candidates are returned. Higher temperatures are more likely to produce unique candidates. Setting temperature=0.0 will always return 1 candidate regardless of the candidate_count. Optional |
topK Top K | string | The API uses combined nucleus and top-k sampling. top_k sets the maximum number of tokens to sample from on each step. Optional |
topP Top P | string | The API uses combined nucleus and top-k sampling. top_p configures the nucleus sampling. It sets the maximum cumulative probability of tokens to sample from. For example, if the sorted probabilities are [0.5, 0.2, 0.1, 0.1, 0.05, 0.05] a top_p of 0.8 will sample as [0.625, 0.25, 0.125, 0, 0, 0]. Typical values are in the [0.9, 1.0] range. Optional |
maxOutputTokens Max Output Tokens | integer | Maximum number of tokens to include in a candidate. Must be greater than zero. If unset, will default to 64. Optional |
stopSequences Stop Sequences | string | A set of up to 5 character sequences that will stop output generation. If specified, the API will stop at the first appearance of a stop sequence. The stop sequence will not be included as part of the response. Optional |
harmCategories Harm Categories | string[] | To set safety settings, select the harm categories to set a threshold for Optional Dynamic |
REFERENCE
Tool details
Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.
- Registry key
- google_palm_api-chat
- Version
- 0.0.3
- App
- Google PaLM
- Authentication
- API key
- Read-only
- No
- Destructive
- No
- Open world
- Yes
- Source
- View on GitHub ↗