Integrations

from openai import OpenAI
from feather import DB
import numpy as np

client = OpenAI()
db = DB.open("embeddings.feather", dim=1536)

# Generate embedding
response = client.embeddings.create(
    model="text-embedding-3-small",
    input="Your text here"
)
vector = np.array(response.data[0].embedding, dtype=np.float32)

# Store in Feather
db.add(1, vector)
db.save()

from sentence_transformers import SentenceTransformer
from feather import DB
import numpy as np

model = SentenceTransformer('all-MiniLM-L6-v2')
db = DB.open("embeddings.feather", dim=384)

text = "Your text here"
embedding = model.encode(text).astype(np.float32)
db.add(1, embedding)
db.save()

import ollama
from feather import DB
import numpy as np

db = DB.open("embeddings.feather", dim=1024)

response = ollama.embeddings(model="nomic-embed-text", prompt="Your text")
vector = np.array(response["embedding"], dtype=np.float32)
db.add(1, vector)
db.save()

from langchain.vectorstores import FeatherVectorStore
from langchain.embeddings import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()
vectorstore = FeatherVectorStore(
    embedding=embeddings,
    db_path="langchain.feather"
)

# Add documents
vectorstore.add_texts(["Document 1", "Document 2"])

# Search
results = vectorstore.similarity_search("query", k=5)

from llama_index.vector_stores import FeatherVectorStore
from llama_index import VectorStoreIndex

vector_store = FeatherVectorStore(db_path="llamaindex.feather")
index = VectorStoreIndex.from_vector_store(vector_store)

# Query
query_engine = index.as_query_engine()
response = query_engine.query("Your question")

import init, { DB } from 'feather-wasm';

await init();
const db = new DB('vectors.feather', 384);

// Use in browser
const vector = new Float32Array(384);
db.add(1, vector);
const results = db.search(query, 5);

// Swift (iOS)
import Feather

let db = try DB.open(path: "vectors.feather", dim: 384)
try db.add(id: 1, vector: vector)
try db.save()