# Semantic search in your files' content | AisDrive

> AisDrive searches for meaning within your documents: it compares your question with the indexed fragments using cosine similarity and returns the relevant paragraph, the source file, and its link.

- **Source (source):** https://aistohire.com/aisdrive-file-manager-116/f/semantic-search-in-your-files
- **Platform (platform):** AIstoHire
- **Language (language):** en

## In summary

- Semantic search in the content of your files
- Ask in your own words and AisDrive compares your question for similarity with the fragments of all your indexed documents: it returns the piece of text that answers, the file it comes from, and its link to open it.
- Search by meaning
- It returns the fragment, not the file
- Complete traceability

## Semantic search in the content of your files

When you send a file to be indexed in AisDrive, its text is extracted, split into fragments of about 400 words with 50 overlapping, and each fragment is converted into a 768-dimensional vector using the gemini-embedding-001 model. That vector is, in practice, the footprint of the fragment's meaning.

When you ask a question, your query is converted into a vector in the same space and compared with the fragments in your drive using cosine similarity. AisDrive retains the 6 closest fragments above a relevance threshold of 0.3, and also prioritizes those that literally contain the keywords from your query: this way, the search works both when you describe the idea with different words and when you remember the exact term.

Each retrieved fragment comes with its origin: file name, folder, relevance percentage, and links to view or download it. It does not return a list of file names that you would have to open one by one, but the specific paragraph and where it came from.

In AisDrive, this search is used from the chat: you write the question in natural language and the answer comes with cited sources, each navigable to its folder. The same retrieval is used by the AI assistant as a tool when it needs to consult your documents. There is (yet) no independent semantic search box in the file view.

## What's included

- **Search by meaning** — you find the document even if you don't use a single word from it, because the comparison is between sense vectors, not between text strings.
- **It returns the fragment, not the file** — you see the paragraph that answers your question, with its relevance percentage, instead of a list of names that you would have to open manually.
- **Complete traceability** — each result comes with the file name, its folder, and links to open or download it, so you can always check the source.
- **Hybrid when needed** — if your query contains a literal term (a code, a proper name, a reference), the snippets that contain it rise in position even if their semantic similarity is low.
- **With noise filtering** — snippets below 0.3 similarity are discarded, so the result is "no relevant content" instead of some random invented paragraph as a response.
- **Search across your entire drive at once** — the query traverses snippets from all your indexed files in AisDrive, not just the folder you are in.
- **Index what you already have** — Word, Excel, PowerPoint, txt, md, csv, json, html, and more are extracted locally at no reading token cost, and PDFs and images go through AI vision.
- **Private by default** — the search is limited to your own content within your account; it does not mix files from other users.

## Frequently Asked Questions

### What is the difference between AisDrive's semantic search and searching by file name?

Searching by name compares letters: if the file is named "final-report-v3.docx" and you search for "construction budget", it won't show up. AisDrive's semantic search compares meanings: it converts your question into a 768-dimensional vector and contrasts it for cosine similarity with the text fragments of your indexed documents, so it finds the paragraph that discusses that budget even if neither the file name nor the text uses your exact words.

### How does AisDrive search within the content of a document?

When indexing a file, AisDrive extracts its text, splits it into chunks of about 400 words with a 50-word overlap, and stores an embedding (768-dimensional vector, gemini-embedding-001 model) for each chunk. When you ask a question, your query is vectorized in the same way and compared to those chunks for cosine similarity; the 6 most relevant results above a threshold of 0.3 are returned, along with their source file, folder, and links.

### Can I search in a file that I haven't indexed?

No. Semantic search only sees the content of indexed files: an uploaded file that is not indexed is stored and can be opened and downloaded normally, but its text is not in the index and therefore does not appear as a result. Indexing is triggered manually per file or automatically by folder if you enable auto-indexing, and it is asynchronous: after uploading a document, you have to wait for its indexing to finish.

### Where is semantic search used within AisDrive?

In the chat. You type the question in natural language in the AisDrive chat panel, and the answer is built from the retrieved snippets, with cited and navigable sources back to their folder. The same retrieval is available as a tool in the platform's AI assistant. There is no separate semantic search box in the file view: access is conversational.

### Does semantic search consume AI tokens?

Vectorizing the query and generating the chat response do consume tokens, just like the embedding of each snippet during indexing. Extracting text from office formats and plain text (docx, xlsx, pptx, txt, md, csv, json, html…) is done locally and recorded at no cost; only PDFs and images require a vision model. In other words: you pay for understanding, not for reading.

- [AisDrive – File Manager](https://aistohire.com/aisdrive-file-manager-116)

## About the platform

**AisDrive – File Manager** — an app by AIstoHire. Available at: https://aistohire.com/aisdrive-file-manager-116/f/semantic-search-in-your-files

### Other languages

- `es`: https://aistohire.com/es/aisdrive-gestor-archivos-116/f/busqueda-semantica-en-tus-archivos
- `fr`: https://aistohire.com/fr/aisdrive-gestionnaire-fichiers-116/f/recherche-semantique-dans-vos-fichiers
- `it`: https://aistohire.com/it/aisdrive-gestore-file-116/f/ricerca-semantica-nei-tuoi-file
- `pt`: https://aistohire.com/pt/aisdrive-gerenciador-arquivos-116/f/busca-semantica-em-seus-arquivos
- `de`: https://aistohire.com/de/aisdrive-dateimanager-116/f/semantische-suche-in-deinen-dateien
- `bg`: https://aistohire.com/bg/aisdrive-menidzhar-na-faylove-za-proekti-ais-to-hire-116/f/semantichno-tarsene-vav-vashite-failove
- `ja`: https://aistohire.com/ja/fairu-kanri-manager-116/f/file-semantic-kensaku
- `nl`: https://aistohire.com/nl/aisdrive-bestandsbeheer-voor-projecten-ais-to-hire-116/f/semantisch-zoeken-in-je-bestanden
- `ko`: https://aistohire.com/ko/aisdrive-file-manager-pail-gwanlija-116/f/paireul-uimi-geomsaek
- `sv`: https://aistohire.com/sv/aisdrive-filhanterare-for-projekt-ais-to-hire-116/f/semantisk-sokning-i-dina-filer
- `da`: https://aistohire.com/da/aisdrive-filhandtering-til-projekter-ais-to-hire-116/f/semantisk-soegning-i-dine-filer
- `ar`: https://aistohire.com/ar/aisdrive-mdir-mlfat-llmsharia-ais-to-hire-116/f/semantic-search-in-your-files
- `no`: https://aistohire.com/no/aisdrive-filbehandler-for-prosjekter-ais-to-hire-116/f/semantisk-sok-i-filene-dine
- `fi`: https://aistohire.com/fi/aisdrive-tiedostonhallinta-projekteille-ais-to-hire-116/f/semanttinen-haku-tiedostoista
- `zh`: https://aistohire.com/zh/aisdrive-file-manager-116/f/wenjian-yuyi-sousuo
- `pl`: https://aistohire.com/pl/aisdrive-menedzer-plikow-dla-projektow-ais-to-hire-116/f/wyszukiwanie-semantyczne-w-plikach
- `he`: https://aistohire.com/he/aisdrive-mnhl-kbtsim-lproiktim-ais-to-hire-116/f/chipus-semanti-bekvatzim-shelcha
- `cs`: https://aistohire.com/cs/aisdrive-spravce-souboru-pro-projekty-ais-to-hire-116/f/semanticke-vyhledavani-v-souborech
- `id`: https://aistohire.com/id/aisdrive-pengelola-file-untuk-proyek-ais-to-hire-116/f/pencarian-semantik-di-berkas-anda
