OVHcloud AI Endpoints

pip install requests openai

import os
import requests
from openai import OpenAI

LIGHTON_API_KEY = os.environ["LIGHTON_API_KEY"]
OVH_AI_ENDPOINTS_ACCESS_TOKEN = os.environ["OVH_AI_ENDPOINTS_ACCESS_TOKEN"]

ovh = OpenAI(
    base_url="https://oai.endpoints.kepler.ai.cloud.ovh.net/v1",
    api_key=OVH_AI_ENDPOINTS_ACCESS_TOKEN,
)


def search(query: str, workspace_id: list[int] | None = None, max_results: int = 5) -> list[dict]:
    payload = {"query": query, "max_results": max_results}
    if workspace_id:
        payload["workspace_id"] = workspace_id

    response = requests.post(
        "https://api.lighton.ai/api/v3/search",
        headers={"Authorization": f"Bearer {LIGHTON_API_KEY}"},
        json=payload,
    )
    response.raise_for_status()
    return response.json()["results"]


def answer(question: str, workspace_id: list[int] | None = None, model: str = "Meta-Llama-3_3-70B-Instruct") -> str:
    results = search(question, workspace_id=workspace_id)

    context = "\n\n".join(
        f"[{r['source']['filename']}, p.{r['source']['page_start']}]\n{r['content']}"
        for r in results
        if r["content"]
    )

    completion = ovh.chat.completions.create(
        model=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


print(answer("What is our data retention policy?"))

import json
import os
import requests
from openai import OpenAI

LIGHTON_API_KEY = os.environ["LIGHTON_API_KEY"]
OVH_AI_ENDPOINTS_ACCESS_TOKEN = os.environ["OVH_AI_ENDPOINTS_ACCESS_TOKEN"]

ovh = OpenAI(
    base_url="https://oai.endpoints.kepler.ai.cloud.ovh.net/v1",
    api_key=OVH_AI_ENDPOINTS_ACCESS_TOKEN,
)

SEARCH_TOOL = {
    "type": "function",
    "function": {
        "name": "lighton_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"],
        },
    },
}


def run_search(query: str, max_results: int = 5) -> str:
    response = requests.post(
        "https://api.lighton.ai/api/v3/search",
        headers={"Authorization": f"Bearer {LIGHTON_API_KEY}"},
        json={"query": query, "max_results": max_results},
    )
    response.raise_for_status()
    results = response.json()["results"]
    passages = [
        f"[{r['source']['filename']}, p.{r['source']['page_start']}]\n{r['content']}"
        for r in results
        if r["content"]
    ]
    return "\n\n".join(passages) if passages else "No results found."


def answer(question: str, model: str = "Meta-Llama-3_3-70B-Instruct") -> str:
    messages = [{"role": "user", "content": question}]

    while True:
        completion = ovh.chat.completions.create(
            model=model,
            tools=[SEARCH_TOOL],
            messages=messages,
        )
        choice = completion.choices[0]

        if choice.finish_reason == "tool_calls":
            messages.append(choice.message)
            for call in choice.message.tool_calls:
                args = json.loads(call.function.arguments)
                result = run_search(**args)
                messages.append({
                    "role": "tool",
                    "tool_call_id": call.id,
                    "content": result,
                })
        else:
            return choice.message.content


print(answer("What is our data retention policy?"))

answer("Summarize the onboarding checklist", workspace_id=[42])

print([m.id for m in ovh.models.list().data])

stream = ovh.chat.completions.create(
    model="Meta-Llama-3_3-70B-Instruct",
    messages=[...],
    stream=True,
)

for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)