Trace · Redis Vector

Trace Redis Vector

Vector Databases

Auto-instrument Redis Vector with traceAI in under 3 minutes. Every LLM call, tool use, retrieval, and chain step becomes an OpenTelemetry span you can search, replay, and debug.

python typescript java · trace evaluate

Start free Open in docs View example on GitHub

Recipes for Redis Vector

Trace Redis Vector live Evaluate Redis Vector

Prerequisites

Before you start

· A working Redis Vector app — local or already in production.
· A free Future AGI account with FI_API_KEY and FI_SECRET_KEY.
· Python 3.9+ / Node 18+ / Java 17+ depending on which SDK you're installing.

Install

pip install traceAI-redis

npm install @traceai/redis

<dependency>
  <groupId>ai.futureagi</groupId>
  <artifactId>traceai-java-redis</artifactId>
  <version>LATEST</version>
</dependency>

Trace recipe

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType
from traceai_redis import RedisInstrumentor

trace_provider = register(
    project_type=ProjectType.OBSERVE,
    project_name="REDIS_APP",
)

RedisInstrumentor().instrument(tracer_provider=trace_provider)

# Your existing Redis Vector code runs unchanged from here.
# Every call is now an OpenTelemetry span in Future AGI.

import { register } from '@traceai/fi-core';
import { RedisInstrumentation } from '@traceai/redis';

const tracerProvider = register({
  projectName: 'redis_app',
  projectType: 'observe',
});

new RedisInstrumentation().instrument({ tracerProvider });

// Your existing Redis Vector code runs unchanged.
// Every call is now an OpenTelemetry span in Future AGI.

import ai.futureagi.fi.instrumentation.TraceProvider;
import ai.futureagi.traceai.redis.RedisInstrumentor;

TraceProvider provider = TraceProvider.builder()
    .projectName("redis_app")
    .projectType("observe")
    .build();

new RedisInstrumentor().instrument(provider);

// Your existing Redis Vector code runs unchanged.
// Every call is now an OpenTelemetry span in Future AGI.

What Future AGI captures

Trace fields you'll see in the dashboard

Spans for every Redis Vector call: input, output, latency, tokens, cost, model name, errors
Trace tree across LLM, tool, retrieval, embedding, and chain spans
Custom attributes via `using_attributes` (session_id, user_id, prompt_template, tags, custom dicts)
Streaming-safe — partial chunks aggregated into a single span

Common gotchas

Read these before you ship

01
Set `FI_API_KEY` and `FI_SECRET_KEY` in env before calling `register()` — silent fallback otherwise.
02
Async frameworks: instantiate the instrumentor *before* you create the client, not after.
03
Streaming responses are aggregated into a single span only when you use the official SDK iterator.

Next: chain it with the other recipes

Trace is the first step. Most teams add an evaluator the same week, and start optimising or simulating once they have a baseline. Each recipe takes minutes to wire up.

Start free Read the Trace docs

Adjacent integrations