Overview
The Materials API includes powerful semantic search capabilities using Retrieval-Augmented Generation (RAG). This allows you to:
- Search materials by meaning, not just keywords
- Find relevant content across all your materials
- Get contextual results with relevance scores
- Search within specific materials or folders
How It Works
Automatic Indexing - When materials are uploaded, they're automatically processed:
- Text is extracted (OCR for PDFs, transcription for audio/video)
- Content is split into chunks
- Vector embeddings are generated
- Embeddings are stored in a vector database
Semantic Search - When you search:
- Your query is converted to a vector embedding
- Similar content is found using vector similarity
- Results are ranked by relevance
Search Materials
Perform a semantic search across all your materials.
JavaScript
const searchResults = await client.v1.materials.search({
query: 'What is photosynthesis and how does it work?',
topK: 5 // Number of results to return
});
searchResults.results.forEach(result => {
console.log(`Score: ${result.score}`);
console.log(`Material: ${result.material?.name}`);
console.log(`Chunk: ${result.text.substring(0, 200)}...`);
console.log('---');
});
Python
search_results = client.v1.materials.search(
query="What is photosynthesis and how does it work?",
top_k=5 # Number of results to return
)
for result in search_results.results:
print(f"Score: {result.score}")
print(f"Material: {result.material.name}")
print(f"Chunk: {result.text[:200]}...")
print("---")
Java
import com.studyfetch.javasdk.models.v1.materials.MaterialSearchParams;
import com.studyfetch.javasdk.models.v1.materials.MaterialSearchResponse;
MaterialSearchParams params = MaterialSearchParams.builder()
.query("What is photosynthesis and how does it work?")
.topK(5) // Number of results to return
.build();
MaterialSearchResponse searchResults = client.v1().materials().search(params);
for (MaterialSearchResponse.Result result : searchResults.results()) {
System.out.println("Score: " + result.score());
System.out.println("Material: " + result.material());
System.out.println("Chunk: " +
result.text().substring(0, Math.min(200, result.text().length())) + "...");
System.out.println("---");
}
C#
using StudyfetchSDK;
using StudyfetchSDK.Models.V1.Materials;
using System;
using System.Threading.Tasks;
public class SearchMaterials
{
public static async Task Search()
{
StudyfetchSDKClient client = new()
{
APIKey = Environment.GetEnvironmentVariable("STUDYFETCH_API_KEY"),
BaseUrl = new Uri("https://studyfetchapi.com")
};
var searchResults = await client.V1.Materials.Search(new MaterialSearchParams()
{
Query = "What is photosynthesis and how does it work?",
TopK = 5 // Number of results to return
});
foreach (var result in searchResults.Results)
{
Console.WriteLine($"Score: {result.Score}");
Console.WriteLine($"Material: {result.Material.Name}");
Console.WriteLine($"Chunk: {result.Text.Substring(0, Math.Min(200, result.Text.Length))}...");
Console.WriteLine("---");
}
}
}
Search Response Format
{
"query": "What is photosynthesis and how does it work?",
"totalResults": 5,
"results": [
{
"score": 0.92,
"text": "Photosynthesis is the process by which plants convert light energy into chemical energy...",
"chunkIndex": 3,
"material": {
"id": "mat_123abc",
"name": "Biology Chapter 3 - Plant Processes",
"contentType": "pdf",
"references": [
{
"title": "Plant Biology Handbook",
"url": "https://example.com/handbook"
}
]
}
},
{
"score": 0.87,
"text": "The light-dependent reactions of photosynthesis occur in the thylakoid membranes...",
"chunkIndex": 5,
"material": {
"id": "mat_456def",
"name": "Plant Biology Textbook",
"contentType": "pdf",
"references": [
{
"title": "Advanced Plant Science",
"url": "https://example.com/advanced-plant-science"
}
]
}
}
]
}
Advanced Search Options
Search with More Results
JavaScript
// Get more results for comprehensive coverage
const results = await client.v1.materials.search({
query: 'cellular respiration and ATP production',
topK: 20 // Get top 20 results
});
console.log(`Found ${results.totalResults} relevant chunks`);
Python
# Get more results for comprehensive coverage
results = client.v1.materials.search(
query="cellular respiration and ATP production",
top_k=20 # Get top 20 results
)
print(f"Found {results.total_results} relevant chunks")
Java
// Get more results for comprehensive coverage
MaterialSearchParams params = MaterialSearchParams.builder()
.query("cellular respiration and ATP production")
.topK(20) // Get top 20 results
.build();
MaterialSearchResponse results = client.v1().materials().search(params);
System.out.println("Found " + results.results().size() + " relevant chunks");
C#
using StudyfetchSDK;
using StudyfetchSDK.Models.V1.Materials;
using System;
using System.Threading.Tasks;
public class SearchWithMoreResults
{
public static async Task SearchMore()
{
StudyfetchSDKClient client = new()
{
APIKey = Environment.GetEnvironmentVariable("STUDYFETCH_API_KEY"),
BaseUrl = new Uri("https://studyfetchapi.com")
};
// Get more results for comprehensive coverage
var results = await client.V1.Materials.Search(new MaterialSearchParams()
{
Query = "cellular respiration and ATP production",
TopK = 20 // Get top 20 results
});
Console.WriteLine($"Found {results.TotalResults} relevant chunks");
}
}
Filter by Material Type
While the current API doesn't support filtering in the search endpoint, you can filter results after retrieval:
JavaScript
const searchResults = await client.v1.materials.search({
query: 'DNA replication process',
topK: 10
});
// Filter for only PDF results
const pdfResults = searchResults.results.filter(
result => result.material?.contentType === 'pdf'
);
console.log(`Found ${pdfResults.length} results in PDFs`);
Python
search_results = client.v1.materials.search(
query="DNA replication process",
top_k=10
)
# Filter for only PDF results
pdf_results = [
result for result in search_results.results
if result.material.content_type == "pdf"
]
print(f"Found {len(pdf_results)} results in PDFs")
Java
import com.studyfetch.javasdk.models.v1.materials.MaterialSearchParams;
import com.studyfetch.javasdk.models.v1.materials.MaterialSearchResponse;
import java.util.List;
import java.util.stream.Collectors;
MaterialSearchResponse searchResults = client.v1().materials().search(
MaterialSearchParams.builder()
.query("DNA replication process")
.topK(10)
.build()
);
// Filter for only PDF results
List<MaterialSearchResponse.Result> pdfResults = searchResults.results().stream()
.filter(result -> result.material().isPresent() &&
"pdf".equals(result.material().get().contentType()))
.collect(Collectors.toList());
System.out.println("Found " + pdfResults.size() + " results in PDFs");
C#
using StudyfetchSDK;
using StudyfetchSDK.Models.V1.Materials;
using System;
using System.Linq;
using System.Threading.Tasks;
public class FilterSearchResults
{
public static async Task FilterByType()
{
StudyfetchSDKClient client = new()
{
APIKey = Environment.GetEnvironmentVariable("STUDYFETCH_API_KEY"),
BaseUrl = new Uri("https://studyfetchapi.com")
};
var searchResults = await client.V1.Materials.Search(new MaterialSearchParams()
{
Query = "DNA replication process",
TopK = 10
});
// Filter for only PDF results
var pdfResults = searchResults.Results
.Where(result => result.Material.ContentType == "pdf")
.ToList();
Console.WriteLine($"Found {pdfResults.Count} results in PDFs");
}
}