Fast Mode

from maximem_synap import MaximemSynapSDK

sdk = MaximemSynapSDK(api_key="your_api_key")

# Fast ingestion for a routine conversation turn
await sdk.memories.create(
    document="User: What's the status of my order?\n"
             "Assistant: Your order #4521 shipped yesterday and should arrive by Thursday.",
    document_type="ai-chat-conversation",
    user_id="user_123",
    customer_id="acme_corp",
    mode="fast"
)
# Returns immediately. Memory available for retrieval within seconds.

# Fast retrieval for a real-time conversation
context = await sdk.conversation.context.fetch(
    conversation_id="conv_123",
    user_id="user_123",
    customer_id="acme_corp",
    search_query=["What do we know about Project Atlas?"],
    mode="fast"
)

# Returns: memories that mention "Project Atlas" directly
# Does NOT return: connected entities (team members, deadlines, decisions)
# unless they co-occur in the same chunks as "Project Atlas"

for fact in context.facts:
    print(f"[{fact.confidence:.2f}] {fact.content}")

# Default: fast mode for real-time chat
context = await sdk.conversation.context.fetch(
    conversation_id=conversation_id,
    user_id=user_id,
    customer_id=customer_id,
    search_query=[user_message],
    mode="fast"
)

# Upgrade to accurate mode when the query is complex
if is_complex_query(user_message):
    context = await sdk.conversation.context.fetch(
        conversation_id=conversation_id,
        user_id=user_id,
        customer_id=customer_id,
        search_query=[user_message],
        mode="accurate"
    )

from maximem_synap import MaximemSynapSDK
from openai import AsyncOpenAI

sdk = MaximemSynapSDK(api_key="synap_api_key")
openai_client = AsyncOpenAI(api_key="openai_api_key")

async def handle_message(user_message: str, user_id: str, customer_id: str, conversation_id: str):
    # Fast retrieval: low latency
    context = await sdk.conversation.context.fetch(
        conversation_id=conversation_id,
        user_id=user_id,
        customer_id=customer_id,
        search_query=[user_message],
        mode="fast"
    )

    response = await openai_client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {
                "role": "system",
                "content": f"You are a helpful assistant.\n\nContext:\n{context.formatted_context}"
            },
            {"role": "user", "content": user_message}
        ]
    )

    assistant_message = response.choices[0].message.content

    # Fast ingestion: returns immediately, processes in 1-5 seconds
    await sdk.memories.create(
        document=f"User: {user_message}\nAssistant: {assistant_message}",
        document_type="ai-chat-conversation",
        user_id=user_id,
        customer_id=customer_id,
        mode="fast"
    )

    return assistant_message

# Fast bootstrap for high-volume, lower-priority data
result = await sdk.memories.batch_create(
    documents=[
        {
            "document": log_entry,
            "document_type": "ai-chat-conversation",
            "document_id": f"log_{entry_id}",
            "user_id": user_id,
            "customer_id": customer_id,
            "mode": "fast"  # Override the default long-range for batch
        }
        for entry_id, log_entry, user_id, customer_id in log_entries
    ],
    fail_fast=False
)