HelixDB Docs

@tags: vector, search, similarity, embedding, searchV, embed, cosine, euclidean, hnsw

Vector Search using `SearchV`

Syntax

SearchV<Type>(vector, limit)

Note: Currently only supports [F64] to represent the vector. Support for [F32] and binary vectors added in the future.

Example 1: Basic vector search

Schema:

V::Document {
    content: String,
    created_at: Date
}

Query:

QUERY SearchVector (vector: [F64], limit: I64) =>
    documents <- SearchV<Document>(vector, limit)
    RETURN documents

QUERY InsertVector (vector: [F64], content: String, created_at: Date) =>
    document <- AddV<Document>(vector, { content: content, created_at: created_at })
    RETURN document

cURL:

curl -X POST \
  http://localhost:6969/InsertVector \
  -H 'Content-Type: application/json' \
  -d '{"vector":[0.1,0.2,0.3,0.4],"content":"Sample document content","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/SearchVector \
  -H 'Content-Type: application/json' \
  -d '{"vector":[0.1,0.2,0.3,0.4],"limit":10}'

Python SDK:

from datetime import datetime, timezone
from helix.client import Client

client = Client(local=True, port=6969)

vector_data = [0.1, 0.2, 0.3, 0.4]
inserted = client.query("InsertVector", {
    "vector": vector_data,
    "content": "Sample document content",
    "created_at": datetime.now(timezone.utc).isoformat(),
})

result = client.query("SearchVector", {
    "vector": vector_data,
    "limit": 10
})
print(result)

TypeScript SDK:

import HelixDB from "helix-ts";

async function main() {
    const client = new HelixDB("http://localhost:6969");

    const vectorData = [0.1, 0.2, 0.3, 0.4];

    const inserted = await client.query("InsertVector", {
        vector: vectorData,
        content: "Sample document content",
        created_at: new Date().toISOString(),
    });

    const result = await client.query("SearchVector", {
        vector: vectorData,
        limit: 10,
    });

    console.log("Search results:", result);
}

main().catch((err) => {
    console.error("SearchVector query failed:", err);
});

Example 2: Vector search with postfiltering

Schema:

V::Document {
    content: String,
    created_at: Date
}

Query:

QUERY SearchRecentDocuments (vector: [F64], limit: I64, cutoff_date: Date) =>
    documents <- SearchV<Document>(vector, limit)::WHERE(_::{created_at}::GTE(cutoff_date))
    RETURN documents

QUERY InsertVector (vector: [F64], content: String, created_at: Date) =>
    document <- AddV<Document>(vector, { content: content, created_at: created_at })
    RETURN document

cURL:

curl -X POST \
  http://localhost:6969/InsertVector \
  -H 'Content-Type: application/json' \
  -d '{"vector":[0.12,0.34,0.56,0.78],"content":"Recent document content","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/InsertVector \
  -H 'Content-Type: application/json' \
  -d '{"vector":[0.15,0.35,0.55,0.75],"content":"Old document content","created_at":"'"$(date -u -d '45 days ago' +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/SearchRecentDocuments \
  -H 'Content-Type: application/json' \
  -d '{"vector":[0.12,0.34,0.56,0.78],"limit":5,"cutoff_date":"'"$(date -u -d '30 days ago' +"%Y-%m-%dT%H:%M:%SZ")"'"}'

Python SDK:

from datetime import datetime, timezone, timedelta
from helix.client import Client

client = Client(local=True, port=6969)

vector_data = [0.12, 0.34, 0.56, 0.78]

recent_date = datetime.now(timezone.utc).isoformat()
old_date = (datetime.now(timezone.utc) - timedelta(days=45)).isoformat()

client.query("InsertVector", {
    "vector": vector_data,
    "content": "Recent document content",
    "created_at": recent_date,
})

client.query("InsertVector", {
    "vector": [0.15, 0.35, 0.55, 0.75],
    "content": "Old document content", 
    "created_at": old_date,
})

cutoff_date = (datetime.now(timezone.utc) - timedelta(days=30)).isoformat()

result = client.query("SearchRecentDocuments", {
    "vector": vector_data,
    "limit": 5,
    "cutoff_date": cutoff_date,
})

print(result)

TypeScript SDK:

import HelixDB from "helix-ts";

async function main() {
    const client = new HelixDB("http://localhost:6969");

    const vectorData = [0.12, 0.34, 0.56, 0.78];

    const recentDate = new Date().toISOString();
    const oldDate = new Date(Date.now() - 45 * 24 * 60 * 60 * 1000).toISOString();

    await client.query("InsertVector", {
        vector: vectorData,
        content: "Recent document content",
        created_at: recentDate,
    });

    await client.query("InsertVector", {
        vector: [0.15, 0.35, 0.55, 0.75],
        content: "Old document content",
        created_at: oldDate,
    });

    const cutoffDate = new Date(Date.now() - 30 * 24 * 60 * 60 * 1000).toISOString();

    const result = await client.query("SearchRecentDocuments", {
        vector: vectorData,
        limit: 5,
        cutoff_date: cutoffDate,
    });

    console.log("Filtered search results:", result);
}

main().catch((err) => {
    console.error("SearchRecentDocuments query failed:", err);
});

Example 3: Using the built in Embed function

Built-in Embed function: don’t need to send array of floats, just send the text.
Schema:

V::Document {
    content: String,
    created_at: Date
}

Query:

QUERY SearchWithText (text: String, limit: I64) =>
    documents <- SearchV<Document>(Embed(text), limit)
    RETURN documents

QUERY InsertTextAsVector (content: String, created_at: Date) =>
    document <- AddV<Document>(Embed(content), { content: content, created_at: created_at })
    RETURN document

Environment variables (OpenAI example):

OPENAI_API_KEY=your_api_key

cURL:

curl -X POST \
  http://localhost:6969/InsertTextAsVector \
  -H 'Content-Type: application/json' \
  -d '{"content":"Introduction to machine learning algorithms","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/InsertTextAsVector \
  -H 'Content-Type: application/json' \
  -d '{"content":"Deep neural networks and AI","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/InsertTextAsVector \
  -H 'Content-Type: application/json' \
  -d '{"content":"Natural language processing techniques","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/SearchWithText \
  -H 'Content-Type: application/json' \
  -d '{"text":"machine learning algorithms","limit":10}'

Python SDK:

from datetime import datetime, timezone
from helix.client import Client

client = Client(local=True, port=6969)

sample_texts = [
    "Introduction to machine learning algorithms",
    "Deep neural networks and AI",
    "Natural language processing techniques"
]

for text in sample_texts:
    client.query("InsertTextAsVector", {
        "content": text,
        "created_at": datetime.now(timezone.utc).isoformat(),
    })

result = client.query("SearchWithText", {
    "text": "machine learning algorithms",
    "limit": 10,
})

print(result)

TypeScript SDK:

import HelixDB from "helix-ts";

async function main() {
    const client = new HelixDB("http://localhost:6969");

    const sampleTexts = [
        "Introduction to machine learning algorithms",
        "Deep neural networks and AI",
        "Natural language processing techniques"
    ];

    for (const text of sampleTexts) {
        await client.query("InsertTextAsVector", {
            content: text,
            created_at: new Date().toISOString(),
        });
    }

    const result = await client.query("SearchWithText", {
        text: "machine learning algorithms",
        limit: 10,
    });

    console.log("Text search results:", result);
}

main().catch((err) => {
    console.error("SearchWithText query failed:", err);
});

Embedding Vectors using `Embed`

Syntax

AddV<Type>(Embed(text))
AddV<Type>(Embed(text), {properties})
SearchV<Type>(Embed(text), limit)

Notes (outdated, will be updated in the future):

The text is automatically embedded with an embedding model of your choice (can be defined in your config.hx.json file).
The default embedding model is text-embedding-ada-002 from OpenAI.
Make sure to set your OPENAI_API_KEY environment variable with your API key in the same location as the queries.hx, schema.hx and config.hx.json files.

Example 1: Creating a vector from text

Schema:

V::Document {
    content: String,
    created_at: Date
}

Query:

QUERY InsertTextAsVector (content: String, created_at: Date) =>
    document <- AddV<Document>(Embed(content), { content: content, created_at: created_at })
    RETURN document

Environment variables (OpenAI example):

OPENAI_API_KEY=your_api_key

cURL:

curl -X POST \
  http://localhost:6969/InsertTextAsVector \
  -H 'Content-Type: application/json' \
  -d '{"content":"Machine learning is transforming the way we work.","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

Python SDK:

from datetime import datetime, timezone
from helix.client import Client

client = Client(local=True, port=6969)

print(client.query("InsertTextAsVector", {
    "content": "Machine learning is transforming the way we work.",
    "created_at": datetime.now(timezone.utc).isoformat(),
}))

TypeScript SDK:

import HelixDB from "helix-ts";

async function main() {
    const client = new HelixDB("http://localhost:6969");

    const result = await client.query("InsertTextAsVector", {
        content: "Machine learning is transforming the way we work.",
        created_at: new Date().toISOString(),
    });

    console.log("Created document vector:", result);
}

main().catch((err) => {
    console.error("InsertTextAsVector query failed:", err);
});

Example 2: Searching with text embeddings

Schema:

V::Document {
    content: String,
    created_at: Date
}

Query:

QUERY SearchWithText (query: String, limit: I64) =>
    documents <- SearchV<Document>(Embed(query), limit)
    RETURN documents

QUERY InsertTextAsVector (content: String, created_at: Date) =>
    document <- AddV<Document>(Embed(content), { content: content, created_at: created_at })
    RETURN document

Environment variables (OpenAI example):

OPENAI_API_KEY=your_api_key

cURL:

curl -X POST \
  http://localhost:6969/InsertTextAsVector \
  -H 'Content-Type: application/json' \
  -d '{"content":"Artificial intelligence is revolutionizing automation","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/InsertTextAsVector \
  -H 'Content-Type: application/json' \
  -d '{"content":"Machine learning algorithms for predictive analytics","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/InsertTextAsVector \
  -H 'Content-Type: application/json' \
  -d '{"content":"Deep learning applications in computer vision","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/SearchWithText \
  -H 'Content-Type: application/json' \
  -d '{"query":"artificial intelligence and automation","limit":5}'

Python SDK:

from datetime import datetime, timezone
from helix.client import Client

client = Client(local=True, port=6969)

sample_texts = [
    "Artificial intelligence is revolutionizing automation",
    "Machine learning algorithms for predictive analytics",
    "Deep learning applications in computer vision"
]

for text in sample_texts:
    client.query("InsertTextAsVector", {
        "content": text,
        "created_at": datetime.now(timezone.utc).isoformat(),
    })

result = client.query("SearchWithText", {
    "query": "artificial intelligence and automation",
    "limit": 5,
})

print(result)

TypeScript SDK:

import HelixDB from "helix-ts";

async function main() {
    const client = new HelixDB("http://localhost:6969");

    const sampleTexts = [
        "Artificial intelligence is revolutionizing automation",
        "Machine learning algorithms for predictive analytics",
        "Deep learning applications in computer vision"
    ];

    for (const text of sampleTexts) {
        await client.query("InsertTextAsVector", {
            content: text,
            created_at: new Date().toISOString(),
        });
    }

    const result = await client.query("SearchWithText", {
        query: "artificial intelligence and automation",
        limit: 5,
    });

    console.log("Search results:", result);
}

main().catch((err) => {
    console.error("SearchWithText query failed:", err);
});

Example 3: Creating a vector and connecting it to a user

Schema:

N::User {
    name: String,
    email: String
}

V::Document {
    content: String,
    created_at: Date
}

E::User_to_Document_Embedding {
    From: User,
    To: Document,
}

Query:

QUERY CreateUserDocument (user_id: ID, content: String, created_at: Date) =>
    document <- AddV<Document>(Embed(content), { content: content, created_at: created_at })
    edge <- AddE<User_to_Document_Embedding>::From(user_id)::To(document)
    RETURN document

QUERY CreateUser (name: String, email: String) =>
    user <- AddN<User>({
        name: name,
        email: email
    })
    RETURN user

Environment variables (OpenAI example):

OPENAI_API_KEY=your_api_key

cURL:

curl -X POST \
  http://localhost:6969/CreateUser \
  -H 'Content-Type: application/json' \
  -d '{"name":"Alice Johnson","email":"alice@example.com"}'

curl -X POST \
  http://localhost:6969/CreateUserDocument \
  -H 'Content-Type: application/json' \
  -d '{"user_id":"<user_id>","content":"This is my personal note about project planning.","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

Python SDK:

from datetime import datetime, timezone
from helix.client import Client

client = Client(local=True, port=6969)

user = client.query("CreateUser", {
    "name": "Alice Johnson",
    "email": "alice@example.com",
})
user_id = user[0]["user"]["id"]

result = client.query("CreateUserDocument", {
    "user_id": user_id,
    "content": "This is my personal note about project planning.",
    "created_at": datetime.now(timezone.utc).isoformat(),
})

print(result)

TypeScript SDK:

import HelixDB from "helix-ts";

async function main() {
    const client = new HelixDB("http://localhost:6969");

    const user = await client.query("CreateUser", {
        name: "Alice Johnson",
        email: "alice@example.com",
    });
    const userId: string = user.user.id;

    const result = await client.query("CreateUserDocument", {
        user_id: userId,
        content: "This is my personal note about project planning.",
        created_at: new Date().toISOString(),
    });

    console.log("Created user document:", result);
}

main().catch((err) => {
    console.error("CreateUserDocument query failed:", err);
});

Example 4: Semantic search with postfiltering

Schema:

V::Document {
    content: String,
    created_at: Date
}

Query:

QUERY SearchRecentNotes (query: String, limit: I64, cutoff_date: Date) =>
    documents <- SearchV<Document>(Embed(query), limit)
                    ::WHERE(_::{created_at}::GTE(cutoff_date))
    RETURN documents

QUERY InsertTextAsVector (content: String, created_at: Date) =>
    document <- AddV<Document>(Embed(content), { content: content, created_at: created_at })
    RETURN document

Environment variables (OpenAI example):

OPENAI_API_KEY=your_api_key

cURL:

curl -X POST \
  http://localhost:6969/InsertTextAsVector \
  -H 'Content-Type: application/json' \
  -d '{"content":"Project milestone review scheduled for next week","created_at":"'"$(date -u +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/InsertTextAsVector \
  -H 'Content-Type: application/json' \
  -d '{"content":"Weekly status report from last month","created_at":"'"$(date -u -d '10 days ago' +"%Y-%m-%dT%H:%M:%SZ")"'"}'

curl -X POST \
  http://localhost:6969/SearchRecentNotes \
  -H 'Content-Type: application/json' \
  -d '{"query":"project deadlines and milestones","limit":10,"cutoff_date":"'"$(date -u -d '7 days ago' +"%Y-%m-%dT%H:%M:%SZ")"'"}'

Python SDK:

from datetime import datetime, timezone, timedelta
from helix.client import Client

client = Client(local=True, port=6969)

recent_date = datetime.now(timezone.utc).isoformat()
old_date = (datetime.now(timezone.utc) - timedelta(days=10)).isoformat()

client.query("InsertTextAsVector", {
    "content": "Project milestone review scheduled for next week",
    "created_at": recent_date,
})

client.query("InsertTextAsVector", {
    "content": "Weekly status report from last month",
    "created_at": old_date,
})

cutoff_date = (datetime.now(timezone.utc) - timedelta(days=7)).isoformat()

result = client.query("SearchRecentNotes", {
    "query": "project deadlines and milestones",
    "limit": 10,
    "cutoff_date": cutoff_date,
})

print(result)

TypeScript SDK:

import HelixDB from "helix-ts";

async function main() {
    const client = new HelixDB("http://localhost:6969");

    const recentDate = new Date().toISOString();
    const oldDate = new Date(Date.now() - 10 * 24 * 60 * 60 * 1000).toISOString();

    await client.query("InsertTextAsVector", {
        content: "Project milestone review scheduled for next week",
        created_at: recentDate,
    });

    await client.query("InsertTextAsVector", {
        content: "Weekly status report from last month",
        created_at: oldDate,
    });

    const cutoffDate = new Date(Date.now() - 7 * 24 * 60 * 60 * 1000).toISOString();

    const result = await client.query("SearchRecentNotes", {
        query: "project deadlines and milestones",
        limit: 10,
        cutoff_date: cutoffDate,
    });

    console.log("Recent search results:", result);
}

main().catch((err) => {
    console.error("SearchRecentNotes query failed:", err);
});

Getting Started

CLI

SDKs

Other Features

Vector Operations

Vector Search using `SearchV`

Syntax

Example 1: Basic vector search

Example 2: Vector search with postfiltering

Example 3: Using the built in Embed function

Embedding Vectors using `Embed`

Syntax

Example 1: Creating a vector from text

Example 2: Searching with text embeddings

Example 3: Creating a vector and connecting it to a user

Example 4: Semantic search with postfiltering

​Vector Search using SearchV

​Syntax

​Example 1: Basic vector search

​Example 2: Vector search with postfiltering

​Example 3: Using the built in Embed function

​Embedding Vectors using Embed

​Syntax

​Example 1: Creating a vector from text

​Example 2: Searching with text embeddings

​Example 3: Creating a vector and connecting it to a user

​Example 4: Semantic search with postfiltering

Vector Search using `SearchV`

Syntax

Example 1: Basic vector search

Example 2: Vector search with postfiltering

Example 3: Using the built in Embed function

Embedding Vectors using `Embed`

Syntax

Example 1: Creating a vector from text

Example 2: Searching with text embeddings

Example 3: Creating a vector and connecting it to a user

Example 4: Semantic search with postfiltering