instructor-xl

!pip install transformers==4.20.0 InstructorEmbedding pinecone sentence-transformers

from pinecone import Pinecone, ServerlessSpec

pc = Pinecone(api_key="API_KEY")

# Create Index
index_name = "instructor-xl"

if not pc.has_index(index_name):
    pc.create_index(
        name=index_name,
        dimension=768,
        metric="cosine",
        spec=ServerlessSpec(
            cloud='aws',
            region='us-east-1'
        )
    )

index = pc.Index(index_name)

# Embed data
data = [
    {"id": "vec1", "text": "Apple is a popular fruit known for its sweetness and crisp texture."},
    {"id": "vec2", "text": "The tech company Apple is known for its innovative products like the iPhone."},
    {"id": "vec3", "text": "Many people enjoy eating apples as a healthy snack."},
    {"id": "vec4", "text": "Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces."},
    {"id": "vec5", "text": "An apple a day keeps the doctor away, as the saying goes."},
]


# using Instructor, we need an instruction to append to passages

instruction = "Represent the following document for retrieval: "

from InstructorEmbedding import INSTRUCTOR

model = INSTRUCTOR('hkunlp/instructor-xl')


# align instructions with text data
# you can vary the instructions by data as well
instruction_embedding_pairs = [[instruction,  d["text"]] for d in data]

embeddings = model.encode(instruction_embedding_pairs)

vectors = []
for d, e in zip(data, embeddings):
    vectors.append({
        "id": d['id'],
        "values": e,
        "metadata": {'text': d['text']}
    })

index.upsert(
    vectors=vectors,
    namespace="ns1"
)

query_instruction = "Represent this query for retrieving supporting documents: "

query = "Tell me about the tech company known as Apple"

x = model.encode([[query_instruction, query]])

results = index.query(
    namespace="ns1",
    vector=x[0].tolist(),
    top_k=3,
    include_values=False,
    include_metadata=True
)

print(results)