Milvus on Future AGI
Vector Databases
Distributed vector database for trillion-scale similarity search.
What you get
Everything traced, scored, and improvable
One install instruments Milvus on OpenTelemetry. Future AGI then layers evaluators, optimisers, and simulations on top of the same trace tree — no second SDK, no double instrumentation.
Trace
Auto-instrumented spans
Every Milvus call becomes a span — inputs, outputs, latency, tokens, cost, model name, tool args, retrieval results, and chain steps captured automatically.
Evaluate
70+ evaluators on every span
Attach Groundedness, Context Relevance, Prompt Injection, Toxicity, and 70+ more — purpose-built scorers powered by the Turing eval models, not generic LLM-as-judge.
Optimize
Closed-loop improvement
Pipe failed traces into agent-opt: GEPA, PromptWizard, ProTeGi, and Bayesian search rewrite your prompts with proof of measured gains.
Simulate
Adversarial scenarios at scale
Generate hundreds of personas and run them through your Milvus agent before launch — text and voice, scripted or persona-driven.
Quickstart · <3 min
Instrument Milvus in three steps
-
Step 1
Install the traceAI package
One package per language, ships from PyPI, npm, and Maven Central.
-
Step 2
Register the trace provider
Set
FI_API_KEYandFI_SECRET_KEY, then callMilvusInstrumentor().instrument(). -
Step 3
Run your existing Milvus app
No code changes. Traces appear in the Future AGI dashboard within seconds.
Install
pip install traceAI-milvusInstrument
from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType
from traceai_milvus import MilvusInstrumentor
trace_provider = register(
project_type=ProjectType.OBSERVE,
project_name="MILVUS_APP",
)
MilvusInstrumentor().instrument(tracer_provider=trace_provider)
# Your existing Milvus code runs unchanged from here.
# Every call is now an OpenTelemetry span in Future AGI.Pick a recipe
What do you want to do with Milvus?
Each recipe is a copy-paste page with the exact code, the gotchas, and a working example you can clone.
Recipes for Milvus
Adjacent integrations
Other vector databases
Pinecone
Managed vector database with hybrid search and metadata filtering.
Weaviate
Open-source vector database with built-in vectorizers and modules.
Qdrant
Vector search engine with payload filtering and quantisation.
Chroma
Embeddings database for AI applications with first-class collections.