Scaleway Generative APIs

Scaleway's Generative APIs expose hosted models (Llama, Mistral, and others) through an OpenAI-compatible endpoint. Pair them with Context212 search to build RAG pipelines where the retrieval stays on Context212's infrastructure and the generation runs on Scaleway.

The flow is:

Search Context212 for the passages most relevant to the user's question.
Pack those passages into the model's context window.
Call the Scaleway model to generate an answer grounded in the retrieved content.

Prerequisites

A C212_API_KEY, available in the Console → API Keys section.
A Scaleway API key with access to Generative APIs, available in the Scaleway console under IAM → API Keys.
At least one workspace with indexed documents on Context212.

Installation

npm install openai

The openai package is used here only for its client; Scaleway's endpoint is fully compatible with it.

Full example

import OpenAI from "openai";

const C212_API_KEY = process.env.C212_API_KEY!;
const SCALEWAY_API_KEY = process.env.SCALEWAY_API_KEY!;

const scaleway = new OpenAI({
  baseURL: "https://api.scaleway.ai/v1",
  apiKey: SCALEWAY_API_KEY,
});

async function search(
  query: string,
  workspaceId?: number[],
  maxResults = 5,
): Promise<Record<string, unknown>[]> {
  const payload: Record<string, unknown> = { query, max_results: maxResults };
  if (workspaceId) payload.workspace_id = workspaceId;

  const response = await fetch("https://api.context212.com/api/v1/search", {
    method: "POST",
    headers: {
      Authorization: `Bearer ${C212_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify(payload),
  });
  if (!response.ok) throw new Error(`Search failed: ${response.status}`);
  return (await response.json()).results;
}

async function answer(
  question: string,
  workspaceId?: number[],
  model = "llama-3.3-70b-instruct",
): Promise<string> {
  const results = await search(question, workspaceId);

  const context = results
    .filter((r: any) => r.content)
    .map(
      (r: any) =>
        `[${r.source.filename}, p.${r.source.page_start}]\n${r.content}`,
    )
    .join("\n\n");

  const completion = await scaleway.chat.completions.create({
    model,
    messages: [
      {
        role: "system",
        content:
          "You are a helpful assistant. Answer the user's question using only " +
          "the provided context. If the context does not contain enough information, " +
          "say so.\n\nContext:\n" +
          context,
      },
      { role: "user", content: question },
    ],
  });
  return completion.choices[0].message.content ?? "";
}

console.log(await answer("What is our data retention policy?"));

Context212 search as a tool

Instead of always searching before calling the model, you can expose Context212 search as a tool and let the model decide when to call it. The model issues an context212_search tool call when it needs context; your code executes the search and feeds the results back; the model then produces a final answer.

import OpenAI from "openai";

const C212_API_KEY = process.env.C212_API_KEY!;
const SCALEWAY_API_KEY = process.env.SCALEWAY_API_KEY!;

const scaleway = new OpenAI({
  baseURL: "https://api.scaleway.ai/v1",
  apiKey: SCALEWAY_API_KEY,
});

const SEARCH_TOOL = {
  type: "function" as const,
  function: {
    name: "context212_search",
    description:
      "Search the company knowledge base for passages relevant to a query. " +
      "Returns ranked excerpts with their source filename and page numbers.",
    parameters: {
      type: "object",
      properties: {
        query: {
          type: "string",
          description: "Natural-language search query.",
        },
        max_results: {
          type: "integer",
          description: "Number of passages to return (1–50, default 5).",
          default: 5,
        },
      },
      required: ["query"],
    },
  },
};

async function runSearch(query: string, maxResults = 5): Promise<string> {
  const response = await fetch("https://api.context212.com/api/v1/search", {
    method: "POST",
    headers: {
      Authorization: `Bearer ${C212_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({ query, max_results: maxResults }),
  });
  if (!response.ok) throw new Error(`Search failed: ${response.status}`);
  const results = (await response.json()).results;
  const passages = results
    .filter((r: any) => r.content)
    .map(
      (r: any) =>
        `[${r.source.filename}, p.${r.source.page_start}]\n${r.content}`,
    );
  return passages.length ? passages.join("\n\n") : "No results found.";
}

async function answer(
  question: string,
  model = "llama-3.3-70b-instruct",
): Promise<string> {
  const messages: OpenAI.Chat.ChatCompletionMessageParam[] = [
    { role: "user", content: question },
  ];

  while (true) {
    const completion = await scaleway.chat.completions.create({
      model,
      tools: [SEARCH_TOOL],
      messages,
    });
    const choice = completion.choices[0];

    if (choice.finish_reason === "tool_calls") {
      messages.push(choice.message);
      for (const call of choice.message.tool_calls ?? []) {
        const args = JSON.parse(call.function.arguments);
        const result = await runSearch(args.query, args.max_results ?? 5);
        messages.push({
          role: "tool",
          tool_call_id: call.id,
          content: result,
        });
      }
    } else {
      return choice.message.content ?? "";
    }
  }
}

console.log(await answer("What is our data retention policy?"));

The loop handles the case where the model issues multiple search calls in sequence before producing a final answer.

Scoping retrieval to a workspace

Pass workspace_id to limit search to a specific workspace. This is useful in multi-tenant products where each customer's data lives in a dedicated workspace.

await answer("Summarize the onboarding checklist", [42]);

Choosing a model

Scaleway's catalog includes several hosted models. Pass the model name to the model parameter:

Model	Notes
`llama-3.3-70b-instruct`	Strong reasoning, good default choice
`llama-3.1-8b-instruct`	Faster and cheaper, suitable for simpler queries
`mistral-nemo-instruct-2407`	Compact Mistral, low latency
`mixtral-8x7b-instruct-v0.1`	MoE model, good for longer contexts

Check the Scaleway documentation for the current model list and regional availability.

Streaming responses

Scaleway's endpoint supports streaming. Enable it by passing stream: true and iterating over the response:

const stream = await scaleway.chat.completions.create({
  model: "llama-3.3-70b-instruct",
  messages: [/* ... */],
  stream: true,
});

for await (const chunk of stream) {
  const delta = chunk.choices[0].delta.content;
  if (delta) process.stdout.write(delta);
}