Rag

Pricing

Pay per usage

Rag

Interviews RAG — An Actor that answers questions about customer meeting notes using RAG. It searches a Pinecone vector store for relevant transcript chunks, ranks results by semantic similarity and recency, then generates answers. Runs in Standby mode as an HTTP service, exposing a /query endpoint.

Pricing

Pay per usage

Rating

0.0

(0)

Developer

👁 Jan Ženíšek

Jan Ženíšek

Maintained by Community

Actor stats

Bookmarked

Total users

Monthly active users

3 months ago

Last modified

Interviews RAG Actor

An Apify Actor that performs Retrieval-Augmented Generation (RAG) on meeting notes stored in Pinecone vector store. It retrieves relevant context and generates answers using GPT-4o.

This Actor runs only in Standby mode as an HTTP server for real-time API requests.

Features

Vector Search: Retrieves relevant documents from Pinecone using similarity search
GPT-4o Integration: Generates comprehensive answers using OpenAI's GPT-4o model
Citation Support: Includes source citations with Notion URLs and dates
Recency-Aware Ranking: Balances semantic similarity with document freshness
Standby Mode: Runs as an HTTP server for real-time API requests
Configurable: Adjustable retrieval parameters (k, threshold, recency)
Per-Request Overrides: API keys, index name, LLM model, and all parameters can be overridden per request

Configuration

Default configuration is loaded from environment variables. All parameters can be overridden per-request.

Variable	Required	Description
`OPENAI_API_KEY`	✅	OpenAI API key for embeddings and LLM
`PINECONE_API_KEY`	✅	Pinecone API key
`INDEX_NAME`	✅	Pinecone index name containing embeddings
`K`	❌	Number of documents to retrieve (default: 20)
`THRESHOLD`	❌	Similarity threshold 0.0-1.0 (default: 0.3)
`RECENCY_WEIGHT`	❌	Balance between similarity and recency 0.0-1.0 (default: 0.2)
`RECENCY_DECAY_DAYS`	❌	Half-life for recency scoring in days (default: 180)
`START_TEMPLATE`	❌	Custom system prompt

Local Development

Create a .env file in the project root:

OPENAI_API_KEY=sk-your-openai-api-key
PINECONE_API_KEY=your-pinecone-api-key
INDEX_NAME=interviews
# Optional
K=20
THRESHOLD=0.3
RECENCY_WEIGHT=0.2

Apify Deployment

Configure environment variables in Actor Settings → Environment Variables on Apify Console.

API Endpoints

Method	Path	Description
`GET`	`/` or `/health`	Health check and configuration status
`POST`	`/` or `/query`	Submit a RAG query
`GET`	`/query?question=...`	Submit query via URL parameters

POST Request

Endpoint: POST /query or POST /

Headers:

Content-Type:application/json

Request Body:

{
"question":"What did customers say about pricing?"
}

Per-request overrides:

All parameters below are optional. If not provided, values from environment variables are used.

Parameter	Type	Description
`openai_api_key`	string	Override OpenAI API key
`pinecone_api_key`	string	Override Pinecone API key
`index_name`	string	Override Pinecone index name
`llm_model`	string	LLM model (default: `gpt-4o`)
`k`	integer	Number of documents to retrieve (1-50)
`threshold`	number	Similarity threshold (0.0-1.0)
`recency_weight`	number	Recency vs similarity balance (0.0-1.0)
`recency_decay_days`	integer	Half-life for recency scoring
`start_template`	string	Custom system prompt

Example with overrides:

{
"question":"What feedback did we get on the new feature?",
"openai_api_key":"sk-your-key",
"pinecone_api_key":"pc-your-key",
"index_name":"custom-index",
"llm_model":"gpt-4o-mini",
"k":5,
"threshold":0.7,
"recency_weight":0.3,
"start_template":"Answer concisely based on the context."
}

Example with cURL:

curl-X POST https://your-actor.apify.actor/query \
-H"Content-Type: application/json"\
-d'{"question": "What are the main customer pain points?"}'

Response

{
"answer":"Based on the meeting notes, customers mentioned several pain points...",
"citations":[
{
"source_number":1,
"notion_url":"https://notion.so/...",
"date":"2025-01-02"
}
],
"sources_used":5
}

Error Response

{
"error":"Missing 'question' field in request body",
"error_type":"validation"
}

Local Development

# Create .env file with your credentials first
# Run locally in Standby mode
ACTOR_STANDBY_PORT=8080 apify run
# Deploy to Apify
apify login
apify push

How It Works

Loads configuration from environment variables at startup
Starts HTTP server listening for requests
For each query:
- Connects to Pinecone and retrieves relevant documents
- Applies recency-aware ranking to prioritize fresh content
- Formats context with source metadata
- Generates answer using GPT-4o with citation instructions
- Extracts and returns citations with the response

👁 Docs To Rag avatar

Docs To Rag

gabrielaxy/docs-to-rag

Transform documentation websites into RAG-ready chunks with semantic understanding, quality scoring, and direct vector database integration.

👁 User avatar

Gabriel Antony Xaviour

👁 RAG Pipeline avatar

RAG Pipeline

labrat011/rag-pipeline

One-click RAG pipeline: chunks text, generates embeddings, and stores vectors in Pinecone or Qdrant. Provide your content and API keys -- the orchestrator handles the rest.

👁 User avatar

mick_

RAG Ingestor: Multi-Source Chunks for Vector DBs

aitoolbreakdown/atb-rag-ingestor

Ingest URLs, sitemaps, and GitHub READMEs into uniform chunks with titles, source URLs, and stable IDs. Ready to push straight into Pinecone, Weaviate, or any RAG pipeline.

👁 User avatar

AI Tool Breakdown

👁 Rag Embedding Generator avatar

Rag Embedding Generator

labrat011/rag-embedding-generator

Generate vector embeddings from text or chunked datasets using OpenAI or Cohere. Chains with RAG Content Chunker for end-to-end RAG pipelines. Outputs raw vectors ready for any vector database.

👁 User avatar

mick_

👁 Website to Text & Markdown — AI / RAG Content Crawler avatar

Website to Text & Markdown — AI / RAG Content Crawler

inexhaustible_glass/rag-website-crawler

Scrape any website into clean text & Markdown with RAG-ready chunks and token counts for LLMs, vector databases (Pinecone, Qdrant) and AI chatbots. Also extracts linked PDF/Word/Excel. Anti-block, robots.txt-aware. Website-to-text for beginners, full RAG pipeline for pros. CPU only, no API key.

👁 User avatar

Hitman studio

Stack Exchange Scraper - Questions, Answers, Tags

wetyr_corporation/stackexchange-scraper

Bulk extract questions and answers from Stack Overflow and any Stack Exchange site. Filter by tag, score, sort. Built for AI/LLM training, developer RAG, and technical research.

👁 User avatar

WETYR

👁 Rag Architect avatar

Rag Architect

ai_solutionist/rag-architect

Transform any website into vector-store-ready knowledge chunks for Pinecone, Weaviate, LangChain, LlamaIndex, Supabase, n8n & more. AI-generated Q&A pairs, smart chunking, PII scrubbing. Build hallucination-free RAG chatbots in minutes.

👁 User avatar

Jason Pellerin

👁 RAG-Ready Documentation Scraper avatar

RAG-Ready Documentation Scraper

alaricus/rag-docs-markdown-scraper

Scrape documentation to framework-optimized Markdown. Features semantic chunking for LLM, vector database, and RAG pipelines. Parse XML sitemaps easily.

👁 User avatar

Alaricus

👁 Rag Knowledge Graph Builder avatar

Rag Knowledge Graph Builder

cspnair/rag-knowledge-graph-builder

Transform websites into RAG-ready datasets. Crawls pages, chunks content into semantic segments (500-1000 tokens), and generates hypothetical questions for each chunk. No API key needed with native mode. Output: pre-indexed JSON optimized for AI retrieval with 3x better accuracy than raw text.

👁 User avatar

csp

129

5.0

👁 Docs-to-RAG Optimizer avatar

Docs-to-RAG Optimizer

vamsi-krishna/docs-to-rag-optimizer

Convert public developer documentation into clean Markdown, semantic RAG chunks, token counts, duplicate hashes, JSONL exports, and quality warnings for AI assistants.

👁 User avatar

Vamsi Krishna

👁 Blog article image

What is a vector database?

URL: https://apify.com/zenisjan/rag

⇱ Rag · Apify

Rag

Interviews RAG Actor

Features

Configuration

Local Development

Apify Deployment

API Endpoints

POST Request

Response

Error Response

Local Development

How It Works

You might also like

Docs To Rag

RAG Pipeline

RAG Ingestor: Multi-Source Chunks for Vector DBs

Rag Embedding Generator

Website to Text & Markdown — AI / RAG Content Crawler

Stack Exchange Scraper - Questions, Answers, Tags

Rag Architect

RAG-Ready Documentation Scraper

Rag Knowledge Graph Builder

Docs-to-RAG Optimizer

Related articles