More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Semantic Search & RAG

    1

    AI-powered semantic search and Retrieval-Augmented Generation (RAG) for intelligent document retrieval, knowledge discovery and context-aware answers with source references.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    AI Semantic Search & RAG

    AI Semantic Search & RAG

    Example session with this skill installed

    Check the health of my local search engine and search the 'chroma' provider for 'How does the chunking logic work?' with natural language answers enabled.

    • Read your context and instructions
    • Compiled the ai semantic search
    • Generated the document

    I have checked the system status and performed the requested semantic search. The service is healthy and currently using the Chroma vector provider.

    Search Results: Chunking Logic

    SourceFilenameScoreContent Preview
    [Source 1]indexing_logic.md0.924The system splits documents into overlapping chunks of 1000 characters...
    [Source 2]api_ref.pdf0.881Text extraction occurs via PDFMiner before being passed to the recursive splitter...

    Answer
    Based on the indexed documents, the chunking logic utilizes a recursive character splitter that creates segments of 1000 characters with a defined overlap to ensure semantic continuity. This process occurs immediately after text extraction from PDF or Markdown files and before the vectors are sent to the Chroma database.

    Next steps

    • If the answer is too brief, I can re-run the search with a higher top_k value.
    • I can list all currently indexed documents in the chroma provider to verify if other relevant files are missing.
    • If you want to compare this result, I can run the same query against Qdrant or Pinecone.

    api_ref.pdf

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    AI Semantic Search & RAG

    Transform your document collections into a searchable AI-powered knowledge base.

    AI Semantic Search & RAG helps developers build intelligent search and question-answering workflows using semantic embeddings, vector databases and Retrieval-Augmented Generation (RAG).

    Key Features

    • Semantic Search: Find relevant information based on meaning rather than exact keywords.
    • Document Processing: Work with PDF, TXT and Markdown documents.
    • RAG Workflows: Retrieve relevant content to support AI-generated answers.
    • Source References: Help users trace answers back to retrieved information.
    • Vector Database Integration: Support workflows using Chroma, Pinecone or Qdrant, depending on configuration.
    • Developer-Friendly: Designed for Python-based AI projects and knowledge-management applications.

    Ideal For

    • Developers building AI assistants.
    • Researchers searching large document collections.
    • Teams developing internal knowledge bases.
    • Students exploring semantic search and RAG.
    • AI automation and document-analysis workflows.

    Requirements

    • Python and the dependencies specified in the package.
    • An OpenAI API key.
    • A configured vector database or supported local storage.
    • Internet access for external API calls.

    Important Notes

    API usage costs are not included in the purchase price. Setup and integration requirements depend on your environment and the supplied package.

    The Skill is intended to assist with document retrieval and grounded question answering. Always verify important answers against their original sources.

    Requires a running AI Search Engine API instance. Limited to PDF, TXT, and Markdown files. No built-in authentication or authorization for API routes.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    OpenAI
    Python 3.12+
    pip
    ChromaDB or Pinecone or Qdrant
    Python
    macOS
    Git

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files
    Environment Variables

    Allowed Hosts

    api.openai.com

    File Scopes

    *.pdf
    *.txt
    *.md
    docs/**
    data/**
    chroma_db/**
    .env

    This skill requires access to local documents to extract text, generate embeddings and build searchable indexes. Terminal access is used to run Python workflows and install dependencies. Network access is required for OpenAI API requests and optional cloud vector database integrations. Environment variables are used to load credentials securely. The skill may write vector indexes, temporary processing files and logs to the configured workspace. Users should review sensitive documents before sending content to external AI services.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill serves as the bridge between your AI agent and your vector database, automating the complex API calls required to index documents and perform semantic searches without manual coding.

    The skill is compatible with any AI agent platform that supports external skill integration and can communicate with a Python-based FastAPI service.

    You will need a separately running instance of the AI Search Engine service, along with an active API key for OpenAI and access to a supported vector provider like Chroma, Pinecone, or Qdrant.

    Yes, this skill is specifically designed to query and compare results from Chroma, Pinecone, and Qdrant simultaneously, allowing you to evaluate which provider gives the best similarity scores for your data.

    You receive the logic and schema definitions that allow your agent to interact with the AI Search Engine REST API, including document management, search execution, and system health monitoring.

    Currently, the skill supports PDF, TXT, and Markdown files for indexing; other file formats must be converted to one of these types before the agent can process them.

    New in LLM Ops