Haystack (deepset) + x711

Add x711 as a Haystack component — plug into any RAG pipeline or agentic workflow.

What you get

Haystack's modular pipeline system lets you drop x711 in as a custom component or tool. Use it in agentic RAG pipelines for live web search, real-time price data, and cross-agent Hive memory — all without hosting any infra. The component below is production-ready.

Step 1 — Config

File: components/x711_tool.py

from haystack import component, default_from_dict
from haystack.tools import Tool
import requests

X711_KEY = "YOUR_KEY"  # free at x711.io — 10 calls/day, no card

# ── Option A: Haystack Tool (for agent pipelines) ─────────────────────────────
def x711_search(query: str) -> str:
    """Search the web via x711."""
    r = requests.post(
        "https://x711.io/api/refuel",
        json={"tool": "web_search", "query": query},
        headers={"X-API-Key": X711_KEY},
        timeout=20,
    )
    return r.json().get("data", "")

def x711_price(symbol: str) -> dict:
    """Get real-time crypto price via x711."""
    r = requests.post(
        "https://x711.io/api/refuel",
        json={"tool": "price_feed", "symbol": symbol},
        headers={"X-API-Key": X711_KEY},
        timeout=20,
    )
    return r.json()

search_tool = Tool(name="x711_web_search", function=x711_search,
    description="Real-time web search for any query.")
price_tool  = Tool(name="x711_price_feed", function=x711_price,
    description="Live crypto price feed (BTC, ETH, SOL, etc.)")

# ── Option B: Custom @component (for RAG pipelines) ──────────────────────────
@component
class X711WebSearch:
    @component.output_types(results=list)
    def run(self, query: str):
        r = requests.post("https://x711.io/api/refuel",
            json={"tool": "web_search", "query": query},
            headers={"X-API-Key": X711_KEY}, timeout=20)
        return {"results": r.json().get("data", [])}

# ── Agent pipeline ────────────────────────────────────────────────────────────
from haystack.components.agents import ToolCallingAgent
from haystack.components.generators.chat import OpenAIChatGenerator

agent = ToolCallingAgent(
    tools=[search_tool, price_tool],
    chat_generator=OpenAIChatGenerator(model="gpt-4o-mini"),
)

Step 2 — Use it

Drop x711 tools into any Haystack agent or custom @component pipeline. Hive memory (hive_read/write) makes a powerful cross-session knowledge layer for production RAG agents.

Sanity check (no install)

curl -X POST https://x711.io/api/refuel \
  -H 'Content-Type: application/json' \
  -d '{"tool":"web_search","query":"latest AI agent frameworks"}'

If that returns JSON with web search results, your network can reach x711.

Available tools

All prices in USDC, billed per call. Free tier waives the first 10 calls/day.

Why x711 is legit

• Open spec. agent.json · OpenAPI 3.1 · x402 manifest
• Open treasury. Every payment lands at 0xb753be5Eac5B29c711051DfF91279834e9C9b9AC on Base — verifiable on-chain.
• Open ledger. /api/attestations publishes every refuel as a hash-chained attestation.
• Live signal. /api/stats/live is an SSE stream of real refuels.

Other frameworks

Get an API key (free) Open API reference