TryRAG

Try RAG on your own document

Try RAG online: add a document, ask a question and see exactly which passages a RAG system would retrieve. Nothing is uploaded.

Document

Settings

For a model you run yourself (Ollama, LM Studio and similar) or one you have an API key for, such as Gemini or Claude. Other models must accept OpenAI-style requests and allow requests from . Requests go straight from your browser to this address.

Examples

Answer

For a written answer, copy the prompt into any AI chat or connect your own model under the document.

Show the prompt



      
Retrieved passages

      
Step by step
How this result was produced
    
    
    
    
  
    

    


    How it works
    Retrieval-augmented generation (RAG) gives an AI model the right passages from your documents when it answers a question. The document is split into passages, each passage is turned into a vector, and the passages closest to the question are placed in the prompt.
    TryRAG lets you try RAG online, free, with nothing to install or sign up for. It shows that process on your own document. The Ask tab shows which passages are retrieved for a question and the prompt they produce, with a step-by-step view of everything in between: the passages, their vectors, the similarity score of each one and a map of where they sit. The Tune tab lets you write test questions, measure how often the right passage is found, and try many settings at once to see which works best.
    It is for learning and for tuning retrieval on small documents. By default it does not write the answer: copy the prompt into an AI chat, or connect a model you run yourself.
    

    Questions
    Can I try RAG online without installing anything?
    Yes. The whole tool runs in your browser. Paste text or upload a PDF, ask a question and you see the retrieved passages straight away. There is no account, no install and nothing is uploaded.
    Can I ask questions about my own PDF?
    Yes. Upload a PDF that contains real text and ask a question. The tool shows the passages it would retrieve, with page numbers. Scanned PDFs, which are images of pages, cannot be read.
    Does it write the answer?
    Not by default. It shows the line of your document that is closest to the question, and builds the prompt, which you can copy into any AI chat. If you run a model on your own computer, or have an API key, you can connect it and get the answer on the page.
    How do I connect my own model?
    Open "Connect your own model" under the document and enter the address and model name. Pick the Ollama, Gemini or Claude example to fill in the address, then add your model name and key. Local programs such as Ollama and LM Studio work if they accept OpenAI-style requests. You may need to allow this site in the program's settings. Requests go straight from your browser to the address you enter.
    How do I tune retrieval?
    In the Tune tab, add questions and the words the right passage must contain. "Test current settings" shows how many questions find that passage. "Try many settings" tests fifteen combinations of splitting method and passage size and lists them best first.
    What is chunk size and overlap?
    Chunk size is how many words go into each passage. Overlap repeats the end of one passage at the start of the next, so a sentence cut at a boundary still appears whole in one of them.
    What is the difference between matching by words and by meaning?
    Word matching finds text that shares words with your question and works instantly. Meaning search uses a small language model that runs in your browser, so it also finds text that says the same thing in different words. It needs a one-time download of about 25 MB.
    Is my text uploaded?
    No. Everything runs in your browser tab. Your documents and questions never leave your device.
    Can my program connect to this tool?
    No. It runs only on this page, for learning and small documents. There is no server or API to connect to.
    

    More
    Chunking Visualizer · Token Counter & Cost Estimator · What is RAG? · How to choose a chunk size for RAG