pgml 1.1.1

The official pgml Rust SDK
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72

from pgml import Collection, Pipeline
from datasets import load_dataset
from time import time
from dotenv import load_dotenv
from rich.console import Console
import asyncio


async def main():
    load_dotenv()
    console = Console()

    # Initialize collection
    collection = Collection("squad_collection")

    # Create and add pipeline
    pipeline = Pipeline(
        "squadv1",
        {
            "text": {
                "splitter": {"model": "recursive_character"},
                "semantic_search": {
                    "model": "Alibaba-NLP/gte-base-en-v1.5",
                },
            }
        },
    )
    await collection.add_pipeline(pipeline)

    # Prep documents for upserting
    data = load_dataset("squad", split="train")
    data = data.to_pandas()
    data = data.drop_duplicates(subset=["context"])
    documents = [
        {"id": r["id"], "text": r["context"], "title": r["title"]}
        for r in data.to_dict(orient="records")
    ]

    # Upsert documents
    await collection.upsert_documents(documents[:200])

    # Query for answer
    query = "Who won more than 20 grammy awards?"
    console.print("Querying for context ...")
    start = time()
    results = await collection.vector_search(
        {
            "query": {
                "fields": {
                    "text": {
                        "query": query,
                        "parameters": {
                            "instruction": "Represent the Wikipedia question for retrieving supporting documents: "
                        },
                    },
                }
            },
            "limit": 5,
        },
        pipeline,
    )
    end = time()
    console.print("\n Results for '%s' " % (query), style="bold")
    console.print(results)
    console.print("Query time = %0.3f" % (end - start))

    # Archive collection
    await collection.archive()


if __name__ == "__main__":
    asyncio.run(main())