Vector Stores

Managed vector database for RAG. Upload documents, we handle chunking, embedding, and search.

Why Vector Stores?

📚

No Infrastructure

Fully managed. No need to run Pinecone, Weaviate, or any database.

🔄

Automatic Processing

We chunk, embed, and index your files automatically.

🔍

Semantic Search

Find relevant content by meaning, not just keywords.

How RAG Works

Retrieval-Augmented Generation
User Query
🔍
Search Vectors
📄
Get Documents
🤖
Generate Answer

Quick Start

Python - Create Vector Store
from mythicdot import MythicDot

client = MythicDot()

# Create a vector store
vector_store = client.vector_stores.create(
    name="Company Knowledge Base"
)

# Upload files (we handle chunking & embedding)
file = client.files.create(
    file=open("company_docs.pdf", "rb"),
    purpose="assistants"
)

# Add file to vector store
client.vector_stores.files.create(
    vector_store_id=vector_store.id,
    file_id=file.id
)

# Wait for processing
while True:
    vs = client.vector_stores.retrieve(vector_store.id)
    if vs.file_counts.completed > 0:
        break
    time.sleep(1)

print(f"Ready! {vs.file_counts.completed} files indexed")

Search Documents

Python - Semantic Search
# Search the vector store
results = client.vector_stores.search(
    vector_store_id=vector_store.id,
    query="What is our refund policy?",
    max_results=5
)

for result in results.data:
    print(f"Score: {result.score:.3f}")
    print(f"Content: {result.content[:200]}...")
    print("---")

Use with Assistants

Python - RAG Assistant
# Create assistant with file search
assistant = client.assistants.create(
    name="Knowledge Assistant",
    model="mythic-4",
    tools=[{"type": "file_search"}],
    tool_resources={
        "file_search": {
            "vector_store_ids": [vector_store.id]
        }
    }
)

# Now ask questions about your documents!
response = client.responses.create(
    model="mythic-4",
    input="What's covered in Chapter 3 of the manual?",
    tools=[{"type": "file_search", "vector_store_ids": [vector_store.id]}]
)

print(response.output_text)

Supported File Types

📄
PDF
.pdf
📝
Word
.docx
📊
PowerPoint
.pptx
📋
Text
.txt, .md
🌐
HTML
.html
📑
JSON
.json
💻
Code
.py, .js, .ts
📈
CSV
.csv

API Reference

Endpoint Method Description
/vector_stores POST Create a new vector store
/vector_stores/{id} GET Retrieve vector store details
/vector_stores/{id}/files POST Add a file to vector store
/vector_stores/{id}/search POST Search for relevant content
/vector_stores/{id} DELETE Delete vector store

Pricing

Storage

$0.10
per GB / day

Searches

Free
included with storage

Free Tier

1 GB
first GB free

💡 Best Practices

For best results, use clean, well-formatted documents. Break large documents into logical sections. Use descriptive filenames. The system automatically handles chunking, but smaller, focused documents often yield better search results.