Exa Search

pip install openai requests

npm install openai

import os

import requests

response = requests.post(
    "https://api.venice.ai/api/v1/augment/search",
    headers={"Authorization": f"Bearer {os.environ['VENICE_API_KEY']}"},
    json={
        "query": "open-source alternatives to vector databases",
        "limit": 5,
        "search_provider": "exa",
    },
    timeout=60,
)
response.raise_for_status()

for result in response.json()["results"]:
    print(result["title"], result["url"])

const response = await fetch("https://api.venice.ai/api/v1/augment/search", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VENICE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    query: "open-source alternatives to vector databases",
    limit: 5,
    search_provider: "exa",
  }),
});
if (!response.ok) throw new Error(`${response.status}: ${await response.text()}`);

for (const result of (await response.json()).results) {
  console.log(result.title, result.url);
}

curl https://api.venice.ai/api/v1/augment/search \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "open-source alternatives to vector databases",
    "limit": 5,
    "search_provider": "exa"
  }'

import json
import os

import requests
from openai import OpenAI

BASE_URL = "https://api.venice.ai/api/v1"
VENICE_API_KEY = os.environ["VENICE_API_KEY"]
MODEL = "z-ai-glm-5-3-flash"

venice = OpenAI(api_key=VENICE_API_KEY, base_url=BASE_URL)

SYSTEM_PROMPT = "Search the web for recent or specific facts. Cite the URL of each source."
TOOLS = [
    {
        "type": "function",
        "function": {
            "name": "web_search",
            "description": "Search the web with Exa. Describe the pages to find in natural language.",
            "parameters": {
                "type": "object",
                "properties": {"query": {"type": "string"}},
                "required": ["query"],
            },
        },
    }
]


def exa_search(query: str, limit: int = 5) -> list[dict]:
    response = requests.post(
        f"{BASE_URL}/augment/search",
        headers={"Authorization": f"Bearer {VENICE_API_KEY}"},
        json={"query": query, "limit": limit, "search_provider": "exa"},
        timeout=60,
    )
    response.raise_for_status()
    return response.json()["results"]


def run_search(call) -> str:
    try:
        query = json.loads(call.function.arguments)["query"]
        return json.dumps(exa_search(query[:400]))
    except Exception as error:
        return f"Error: {error}"


def ask(question: str, max_rounds: int = 6) -> str:
    messages = [
        {"role": "system", "content": SYSTEM_PROMPT},
        {"role": "user", "content": question},
    ]
    for _ in range(max_rounds):
        completion = venice.chat.completions.create(
            model=MODEL,
            messages=messages,
            tools=TOOLS,
            extra_body={"venice_parameters": {"include_venice_system_prompt": False}},
        )
        message = completion.choices[0].message
        if not message.tool_calls:
            return message.content
        messages.append(message)
        for call in message.tool_calls:
            messages.append({"role": "tool", "tool_call_id": call.id, "content": run_search(call)})
    raise RuntimeError(f"No answer after {max_rounds} rounds")


print(ask("What changed in the latest stable release of Python?"))

import OpenAI from "openai";

const BASE_URL = "https://api.venice.ai/api/v1";
const MODEL = "z-ai-glm-5-3-flash";

const venice = new OpenAI({ apiKey: process.env.VENICE_API_KEY, baseURL: BASE_URL });

const SYSTEM_PROMPT = "Search the web for recent or specific facts. Cite the URL of each source.";
const tools = [
  {
    type: "function",
    function: {
      name: "web_search",
      description: "Search the web with Exa. Describe the pages to find in natural language.",
      parameters: {
        type: "object",
        properties: { query: { type: "string" } },
        required: ["query"],
      },
    },
  },
];

async function exaSearch(query, limit = 5) {
  const response = await fetch(`${BASE_URL}/augment/search`, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.VENICE_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({ query, limit, search_provider: "exa" }),
  });
  if (!response.ok) throw new Error(`${response.status}: ${await response.text()}`);
  return (await response.json()).results;
}

async function runSearch(call) {
  try {
    const { query } = JSON.parse(call.function.arguments);
    return JSON.stringify(await exaSearch(query.slice(0, 400)));
  } catch (error) {
    return `Error: ${error.message}`;
  }
}

async function ask(question, maxRounds = 6) {
  const messages = [
    { role: "system", content: SYSTEM_PROMPT },
    { role: "user", content: question },
  ];
  for (let round = 0; round < maxRounds; round++) {
    const completion = await venice.chat.completions.create({
      model: MODEL,
      messages,
      tools,
      venice_parameters: { include_venice_system_prompt: false },
    });
    const message = completion.choices[0].message;
    if (!message.tool_calls?.length) return message.content;
    messages.push(message);
    for (const call of message.tool_calls) {
      messages.push({ role: "tool", tool_call_id: call.id, content: await runSearch(call) });
    }
  }
  throw new Error(`No answer after ${maxRounds} rounds`);
}

console.log(await ask("What changed in the latest stable release of Python?"));

question = "What are the main techniques for reducing LLM inference latency?"

results = exa_search(question, limit=8)
sources = "\n\n".join(
    f"[{i}] {result['title']}\n{result['url']}\n{result['content']}"
    for i, result in enumerate(results, start=1)
)

completion = venice.chat.completions.create(
    model=MODEL,
    messages=[
        {
            "role": "system",
            "content": "Answer only from the numbered sources. Cite each claim by number, like [2].",
        },
        {"role": "user", "content": f"Question: {question}\n\nSources:\n\n{sources}"},
    ],
    extra_body={"venice_parameters": {"include_venice_system_prompt": False}},
)

print(completion.choices[0].message.content)
for i, result in enumerate(results, start=1):
    print(f"[{i}] {result['url']}")

const question = "What are the main techniques for reducing LLM inference latency?";

const results = await exaSearch(question, 8);
const sources = results
  .map((r, i) => `[${i + 1}] ${r.title}\n${r.url}\n${r.content}`)
  .join("\n\n");

const completion = await venice.chat.completions.create({
  model: MODEL,
  messages: [
    {
      role: "system",
      content: "Answer only from the numbered sources. Cite each claim by number, like [2].",
    },
    { role: "user", content: `Question: ${question}\n\nSources:\n\n${sources}` },
  ],
  venice_parameters: { include_venice_system_prompt: false },
});

console.log(completion.choices[0].message.content);
results.forEach((r, i) => console.log(`[${i + 1}] ${r.url}`));

from exa_py import Exa

exa = Exa()  # reads EXA_API_KEY
TOOLS = [
    exa.openai.web_search(),
    exa.openai.get_contents(text={"max_characters": 10000}),
]

import Exa from "exa-js";

const exa = new Exa(); // reads EXA_API_KEY
const tools = [
  exa.openai.webSearch(),
  exa.openai.getContents({ text: { maxCharacters: 10000 } }),
];