> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mavera.io/llms.txt
> Use this file to discover all available pages before exploring further.
# Review Excerpt Sentiment
> Quick sentiment classification of Yelp review excerpts using Mavera Chat
## Scenario
You need a quick sentiment read on a specific business — is the trend positive or negative? Yelp's API returns up to 3 review excerpts per business (full reviews require scraping, which violates ToS). You pull these excerpts and send them to Mavera Chat for rapid sentiment classification. It's a fast signal — not deep analysis — useful for screening competitors or monitoring your own listings.
**Flow:** Yelp `GET /businesses/{id}/reviews` → Up to 3 excerpts → Mavera `POST /responses` → Quick sentiment classification
## Architecture
```mermaid theme={"dark"}
flowchart LR
A["Yelp GET /businesses/{id}/reviews"] --> B["Up to 3 review excerpts"]
B --> C["POST /api/v1/responses"]
C --> D["Quick sentiment summary"]
```
## Code
```python Python theme={"dark"}
import os, requests, json
from openai import OpenAI
YELP = os.environ["YELP_API_KEY"]
MV = os.environ["MAVERA_API_KEY"]
YELP_H = {"Authorization": f"Bearer {YELP}"}
# 1. Get business details + reviews
BUSINESS_IDS = [
"houndstooth-coffee-austin",
"fleet-coffee-austin",
"merit-coffee-austin",
]
mavera = OpenAI(api_key=MV, base_url="https://app.mavera.io/api/v1")
results = []
for biz_id in BUSINESS_IDS:
# Business details
biz = requests.get(f"https://api.yelp.com/v3/businesses/{biz_id}",
headers=YELP_H).json()
name = biz.get("name", biz_id)
rating = biz.get("rating", 0)
review_count = biz.get("review_count", 0)
# Review excerpts (max 3)
revs = requests.get(f"https://api.yelp.com/v3/businesses/{biz_id}/reviews",
headers=YELP_H).json().get("reviews", [])
excerpt_block = "\n".join(
f"[{r.get('rating',0)}/5] {r.get('text','')[:300]}"
for r in revs
)
# 2. Quick sentiment via Mavera Chat
response = mavera.responses.create(model="mavera-1",
input=[{"role": "user", "content": f"""Quick sentiment analysis for {name} ({rating}/5, {review_count} reviews).
Review excerpts:
{excerpt_block}
Return JSON: {{
"sentiment": "positive|negative|mixed",
"confidence": 0-1,
"key_themes": ["theme1", "theme2"],
"one_line_summary": "..."
}}"""}],
extra_body={"response_format": {"type": "json_object"}})
parsed = json.loads(response.output[0].content[0].text)
results.append({"name": name, "rating": rating, "reviews": review_count, **parsed})
print(f"{name}: {parsed.get('sentiment','')} ({parsed.get('confidence',0):.0%}) — {parsed.get('one_line_summary','')}")
# 3. Summary
print(f"\n=== Sentiment Summary ({len(results)} businesses) ===")
for r in results:
emoji = {"positive": "↑", "negative": "↓", "mixed": "→"}.get(r.get("sentiment", ""), "?")
print(f" {emoji} {r['name']}: {r['rating']}/5, {r.get('sentiment','?')}, themes: {', '.join(r.get('key_themes', []))}")
```
```javascript JavaScript theme={"dark"}
const OpenAI = require("openai").default;
const YELP = process.env.YELP_API_KEY;
const MV = process.env.MAVERA_API_KEY;
const YELP_H = { Authorization: `Bearer ${YELP}` };
const BUSINESS_IDS = ["houndstooth-coffee-austin", "fleet-coffee-austin", "merit-coffee-austin"];
const mavera = new OpenAI({ apiKey: MV, baseURL: "https://app.mavera.io/api/v1" });
const results = [];
for (const bizId of BUSINESS_IDS) {
const biz = await fetch(`https://api.yelp.com/v3/businesses/${bizId}`, { headers: YELP_H })
.then((r) => r.json());
const revs = await fetch(`https://api.yelp.com/v3/businesses/${bizId}/reviews`, { headers: YELP_H })
.then((r) => r.json()).then((d) => d.reviews || []);
const excerpts = revs.map((r) => `[${r.rating}/5] ${(r.text || "").slice(0, 300)}`).join("\n");
const response = await mavera.responses.create({
model: "mavera-1",
input: [{ role: "user", content: `Sentiment for ${biz.name} (${biz.rating}/5, ${biz.review_count} reviews):\n\n${excerpts}\n\nReturn JSON: {sentiment, confidence, key_themes, one_line_summary}` }],
extra_body: { response_format: { type: "json_object" } },
});
const parsed = JSON.parse(response.output[0].content[0].text);
results.push({ name: biz.name, rating: biz.rating, ...parsed });
console.log(`${biz.name}: ${parsed.sentiment} (${(parsed.confidence * 100).toFixed(0)}%) — ${parsed.one_line_summary}`);
}
console.log(`\n=== Summary (${results.length}) ===`);
results.forEach((r) => {
const arrow = { positive: "↑", negative: "↓", mixed: "→" }[r.sentiment] || "?";
console.log(` ${arrow} ${r.name}: ${r.rating}/5, ${r.sentiment}, themes: ${(r.key_themes || []).join(", ")}`);
});
```
## Example Output
```json theme={"dark"}
{
"businesses_analyzed": 3,
"results": [
{
"name": "Houndstooth Coffee",
"rating": 4.5,
"sentiment": "positive",
"confidence": 0.92,
"key_themes": ["espresso quality", "minimalist design", "knowledgeable staff"],
"one_line_summary": "Consistently praised for exceptional espresso and curated ambiance."
},
{
"name": "Fleet Coffee",
"rating": 4.0,
"sentiment": "mixed",
"confidence": 0.71,
"key_themes": ["outdoor seating", "food truck partnerships", "parking challenges"],
"one_line_summary": "Loved for the outdoor vibe, dinged for limited parking and inconsistent hours."
},
{
"name": "Merit Coffee",
"rating": 4.5,
"sentiment": "positive",
"confidence": 0.88,
"key_themes": ["single-origin beans", "pour-over quality", "friendly baristas"],
"one_line_summary": "Strong loyal following for pour-over enthusiasts; consistently high marks."
}
]
}
```
## Error Handling
Yelp's API returns a maximum of 3 review excerpts per business. This is a ToS limitation — do not scrape for more. Use the excerpts as a directional signal only.
Yelp uses URL-slug-style IDs (e.g., `houndstooth-coffee-austin`). Find them via business search or from Yelp page URLs.
With only 3 excerpts, confidence should be interpreted loosely. Flag any result with confidence below 0.6 as "insufficient data."