1# File Search Tool
2 
3Enables agents to search through uploaded files using semantic and keyword search from vector stores. Supports a wide range of file formats including PDF, Markdown, Word, and more.
4 
5> ⚠️ **Important:** Before creating an agent with file search, you **must** read the official documentation linked in the References section to understand prerequisites, supported file types, and vector store setup.
6 
7## Prerequisites
8 
9- A [basic or standard agent environment](https://learn.microsoft.com/azure/ai-foundry/agents/environment-setup)
10- A **vector store** must be created before the agent — the `file_search` tool requires `vector_store_ids`
11- Files must be uploaded to the vector store before the agent can search them
12 
13## Key Concepts
14 
15| Concept | Description |
16|---------|-------------|
17| **Vector Store** | A container that indexes uploaded files for semantic search. Must be created first. |
18| **vector_store_ids** | Required parameter on the `file_search` tool — references the vector store(s) to search. |
19| **File upload** | Files are uploaded to the project, then attached to a vector store for indexing. |
20 
21## Setup Workflow
22 
23```
241. Create a vector store (REST API: POST /vector_stores)
25   │
26   ▼
272. (Optional) Upload files and attach to vector store
28   │
29   ▼
303. Create agent with file_search tool referencing the vector_store_ids
31   │
32   ▼
334. Agent can now search files in the vector store
34```
35 
36> ⚠️ **Warning:** Creating an agent with `file_search` without providing `vector_store_ids` will fail with a `400 BadRequest` error: `required: Required properties ["vector_store_ids"] are not present`.
37 
38## REST API Notes
39 
40When creating vector stores via `az rest`:
41 
42| Parameter | Value |
43|-----------|-------|
44| **Endpoint** | `https://<resource>.services.ai.azure.com/api/projects/<project>/vector_stores` |
45| **API version** | `v1` |
46| **Auth resource** | `https://ai.azure.com` |
47 
48## Troubleshooting
49 
50| Error | Cause | Fix |
51|-------|-------|-----|
52| `vector_store_ids` not present | Agent created without vector store | Create a vector store first, then pass its ID |
53| 401 Unauthorized | Wrong auth resource for REST API | Use `--resource "https://ai.azure.com"` with `az rest` |
54| Bad API version | Using ARM-style API version | Use `api-version=v1` for the data-plane vector store API |
55| No search results | Vector store is empty | Upload files to the vector store before querying |
56 
57## References
58 
59- [File Search tool documentation](https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools/file-search?view=foundry&pivots=python)
60- [Tool Catalog](https://learn.microsoft.com/azure/ai-foundry/agents/concepts/tool-catalog?view=foundry)
61