Skip to main content
The most common Velixar use case: make your chatbot remember users across sessions.

​
Architecture

User → Your Chatbot → LLM
                ↕
            Velixar API
        (store + recall memories)

​
Implementation

import requests
import openai

VELIXAR_KEY = "vlx_your_key"
VELIXAR_URL = "https://api.velixarai.com/v1"
headers = {"Authorization": f"Bearer {VELIXAR_KEY}"}

def chat(user_id: str, message: str) -> str:
    # 1. Recall relevant memories
    memories = requests.get(f"{VELIXAR_URL}/memory/search",
        headers=headers,
        params={"q": message, "user_id": user_id, "limit": 5}
    ).json().get("memories", [])

    context = "\n".join(f"- {m['content']}" for m in memories)

    # 2. Call LLM with memory context
    response = openai.chat.completions.create(
        model="gpt-4",
        messages=[
            {"role": "system", "content": f"You remember this about the user:\n{context}"},
            {"role": "user", "content": message}
        ]
    )
    reply = response.choices[0].message.content

    # 3. Store the exchange as a memory
    requests.post(f"{VELIXAR_URL}/memory",
        headers=headers,
        json={
            "content": f"User said: {message}\nAssistant replied: {reply[:200]}",
            "user_id": user_id,
            "tier": 2,
            "type": "context"
        })

    return reply
That’s it. Your chatbot now remembers every user across sessions.