v0.0.11 #116
Assignees
Comments
This was referenced Aug 31, 2023
Merged
SimpleVectorIndex refactorThe internal structure should be like this: type data struct {
ID string `json:"id"`
Metadata types.Meta `json:"metadata"`
Embedding embedder.Embedding `json:"embedding"`
} |
This was referenced Sep 13, 2023
Merged
Merged
Redis integrationcreate indexinsert vector with medatadasearch with vectorGo string vector encodinga := []float32{0.1,0.2,0.3}
e := fmt.Sprintf("%q",a) |
import json
import time
import numpy as np
import pandas as pd
import redis
import requests
from redis.commands.search.field import (
NumericField,
TagField,
TextField,
VectorField,
)
from redis.commands.search.indexDefinition import IndexDefinition, IndexType
from redis.commands.search.query import Query
# from sentence_transformers import SentenceTransformer
url = "https://raw.githubusercontent.com/bsbodden/redis_vss_getting_started/main/data/bikes.json"
response = requests.get(url)
bikes = response.json()
client = redis.Redis(host="localhost", port=6379, decode_responses=True)
res = client.ping()
# >>> True
client.flushall()
pipeline = client.pipeline()
for i, bike in enumerate(bikes, start=1):
redis_key = f"bikes:{i:03}"
pipeline.json().set(redis_key, "$", bike)
res = pipeline.execute()
# >>> [True, True, True, True, True, True, True, True, True, True, True]
res = client.json().get("bikes:001", "$.model")
# >>> ['Summit']
keys = sorted(client.keys("bikes:*"))
# >>> ['bikes:001', 'bikes:002', ..., 'bikes:011']
descriptions = client.json().mget(keys, "$.description")
descriptions = [item for sublist in descriptions for item in sublist]
# embedder = SentenceTransformer("msmarco-distilbert-base-v4")
# embeddings = embedder.encode(descriptions).astype(np.float32).tolist()
embeddings = np.random.rand(len(bikes), 4).astype(np.float32).tolist()
VECTOR_DIMENSION = len(embeddings[0])
# >>> 768
pipeline = client.pipeline()
for key, embedding in zip(keys, embeddings):
pipeline.json().set(key, "$.description_embeddings", embedding)
pipeline.execute()
# >>> [True, True, True, True, True, True, True, True, True, True, True]
res = client.json().get("bikes:0")
# >>>
# {
# "model": "Summit",
# "brand": "nHill",
# "price": 1200,
# "type": "Mountain Bike",
# "specs": {
# "material": "alloy",
# "weight": "11.3"
# },
# "description": "This budget mountain bike from nHill performs well..."
# "description_embeddings": [
# -0.538114607334137,
# -0.49465855956077576,
# -0.025176964700222015,
# ...
# ]
# }
schema = (
TextField("$.model", no_stem=True, as_name="model"),
TextField("$.brand", no_stem=True, as_name="brand"),
NumericField("$.price", as_name="price"),
TagField("$.type", as_name="type"),
TextField("$.description", as_name="description"),
VectorField(
"$.description_embeddings",
"FLAT",
{
"TYPE": "FLOAT32",
"DIM": VECTOR_DIMENSION,
"DISTANCE_METRIC": "COSINE",
},
as_name="vector",
),
)
definition = IndexDefinition(prefix=["bikes:"], index_type=IndexType.JSON)
res = client.ft("idx:bikes_vss").create_index(
fields=schema, definition=definition
)
# >>> 'OK'
query = (
Query('(*)=>[KNN 3 @vector $query_vector AS vector_score]')
.sort_by('vector_score')
.return_fields('vector_score', 'id', 'brand', 'model', 'description')
.dialect(2)
)
encoded_query = [0.1, 0.2, 0.3, 0.4]
docs = client.ft("idx:bikes_vss").search(query, {'query_vector': np.array(
encoded_query, dtype=np.float32).tobytes()}).docs
print(docs) |
MetricsHere are the typical ranges for the following mathematical functions:
Keep in mind that these are the general ranges for these mathematical functions, but their specific application and interpretation can vary depending on the context in which they are used. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
load()insimpleVectorIndexChore Fix load() in SimpleVectorIndex #123The text was updated successfully, but these errors were encountered: