Integrations
Flowise is an open-source visual builder for LLM apps. Connect it to DEVUP AI to run chatbots, agents and document Q&A on DEVUP AI models, then call them from your apps or your website.
mkdir flowise-app
cd flowise-app
npm init -y
npm install flowise
npx flowise startOpen http://localhost:3000.
| Variable | Purpose |
|---|---|
| DATABASE_PATH | folder for the Flowise database |
| SECRETKEY_PATH | folder for Flowise's encryption key |
| LOG_PATH | folder for logs |
| BLOB_STORAGE_PATH | folder for uploaded files |
| DISABLE_FLOWISE_TELEMETRY | true turns telemetry off |
Add OpenAI Custom Model to a flow and fill in:
| Setting | Value |
|---|---|
| Connect Credential | DEVUP AI |
| Model Name | a DEVUP AI catalog ID, such as deepseek-ai/DeepSeek-V4-Pro |
| Base Path (Additional Parameters) | https://api.devupai.com/v1 |
| Streaming | on |
https://api.devupai.com/v1
Connect OpenAI Custom Model and Buffer Memory to a Conversation Chain, save, and open the chat.
Reply with exactly: Salam DEVUP
Connect OpenAI Custom Model, Buffer Memory and the Calculator tool to a Tool Agent.
What is 12 multiplied by 34? Use the calculator tool.
Flowise shows the calculator tool above the answer.
Try it with this file:
DEVUP AI internal note.
The warehouse access code for the Oran branch is DZ-7719.
The Algiers branch opens at 8:30.What is the warehouse access code for the Oran branch?
The files contain no credentials; each person selects their own after loading.
Open the </> button on a saved flow to get its ID and ready-made Python, JavaScript and cURL snippets. From PowerShell:
$id = "YOUR_CHATFLOW_ID"
$r = Invoke-RestMethod -Uri "http://localhost:3000/api/v1/prediction/$id" -Method Post -ContentType "application/json" -Body '{"question":"Reply with exactly: Salam DEVUP"}'
$r.text
Paste this into your page, with your flow ID and your Flowise address:
<script type="module">
import Chatbot from "https://cdn.jsdelivr.net/npm/flowise-embed/dist/web.js"
Chatbot.init({ chatflowid: "YOUR_CHATFLOW_ID", apiHost: "http://localhost:3000" })
</script>
An embedded chatbot sends no API key, so keep its flow on No Authorization.
$id = "YOUR_CHATFLOW_ID"
$r = Invoke-RestMethod -Uri "http://localhost:3000/api/v1/prediction/$id" -Method Post -ContentType "application/json" -Headers @{ Authorization = "Bearer YOUR_FLOWISE_API_KEY" } -Body '{"question":"Reply with exactly: Salam DEVUP"}'
$r.textUse exact catalog IDs: a chat model in OpenAI Custom Model, and BAAI/bge-m3 in OpenAI Custom Embedding. Agents need a model with tool calling. See the Models catalog, Embeddings guide, and Tool Calling guide.
Add this to the package.json of your Flowise folder, delete node_modules, and run npm install again:
"overrides": {
"better-sqlite3": "12.11.1"
}Yes. Add an OpenAI API credential with your DEVUP AI key, then use OpenAI Custom Model with Base Path https://api.devupai.com/v1.
Yes. Use OpenAI Custom Embedding with BAAI/bge-m3 and the same Base Path, then upsert your files into a vector store.
Every chat and embedding request is a regular DEVUP AI API call, metered in Algerian Dinar on your account.
Yes. Copy the snippet from the Embed tab of the flow's </> button and paste it into your page.
Create a Flowise API key, select it on the flow, and send it as a Bearer token. An embedded chatbot needs its flow on No Authorization.
Yes. Download the chatbot, agent or document Q&A flow from this page, load it in Flowise, and pick your DEVUP AI credential.