Semantic search - quickstart

$	pip install -U cohere

import cohere
co = cohere.ClientV2(
    "COHERE_API_KEY"
)  # Get your free API key here: https://dashboard.cohere.com/api-keys

# Define the documents
documents = [
    "Joining Slack Channels: Be sure to join relevant channels to stay informed and engaged.",
    "Finding Coffee Spots: For your caffeine fix, cross the street to the café for artisan coffee.",
    "Working Hours Flexibility: While our core hours are 9 AM to 5 PM, we offer flexibility to adjust as needed.",
]
# Embed the documents
doc_emb = co.embed(
    model="embed-v4.0",
    input_type="search_document",
    texts=documents,
    embedding_types=["float"],
).embeddings.float

# Add the user query
query = "Ways to connect with my teammates"
# Embed the query
query_emb = co.embed(
    model="embed-v4.0",
    input_type="search_query",
    texts=[query],
    embedding_types=["float"],
).embeddings.float

import numpy as np
# Compute dot product similarity and display results
def return_results(query_emb, doc_emb, documents):
    n = 2  # customize your top N results
    scores = np.dot(query_emb, np.transpose(doc_emb))[0]
    max_idx = np.argsort(-scores)[:n]
    for rank, idx in enumerate(max_idx):
        print(f"Rank: {rank+1}")
        print(f"Score: {scores[idx]}")
        print(f"Document: {documents[idx]}\n")
return_results(query_emb, doc_emb, documents)

Rank: 1
Score: 0.262197161387274
Document: Joining Slack Channels: Be sure to join relevant channels to stay informed and engaged.
Rank: 2
Score: 0.1266074257723145
Document: Working Hours Flexibility: While our core hours are 9 AM to 5 PM, we offer flexibility to adjust as needed.

$	pip install -U cohere

import cohere
co = cohere.ClientV2(
    "COHERE_API_KEY"
)  # Get your free API key here: https://dashboard.cohere.com/api-keys

# Define the documents
documents = [
    "Joining Slack Channels: Be sure to join relevant channels to stay informed and engaged.",
    "Finding Coffee Spots: For your caffeine fix, cross the street to the café for artisan coffee.",
    "Working Hours Flexibility: While our core hours are 9 AM to 5 PM, we offer flexibility to adjust as needed.",
]
# Embed the documents
doc_emb = co.embed(
    model="embed-v4.0",
    input_type="search_document",
    texts=documents,
    embedding_types=["float"],
).embeddings.float

# Add the user query
query = "Ways to connect with my teammates"
# Embed the query
query_emb = co.embed(
    model="embed-v4.0",
    input_type="search_query",
    texts=[query],
    embedding_types=["float"],
).embeddings.float

import numpy as np
# Compute dot product similarity and display results
def return_results(query_emb, doc_emb, documents):
    n = 2  # customize your top N results
    scores = np.dot(query_emb, np.transpose(doc_emb))[0]
    max_idx = np.argsort(-scores)[:n]
    for rank, idx in enumerate(max_idx):
        print(f"Rank: {rank+1}")
        print(f"Score: {scores[idx]}")
        print(f"Document: {documents[idx]}\n")
return_results(query_emb, doc_emb, documents)

Rank: 1
Score: 0.262197161387274
Document: Joining Slack Channels: Be sure to join relevant channels to stay informed and engaged.
Rank: 2
Score: 0.1266074257723145
Document: Working Hours Flexibility: While our core hours are 9 AM to 5 PM, we offer flexibility to adjust as needed.

1	import cohere
2
3	co = cohere.ClientV2(
4	"COHERE_API_KEY"
5	) # Get your free API key here: https://dashboard.cohere.com/api-keys

1	# Define the documents
2	documents = [
3	"Joining Slack Channels: Be sure to join relevant channels to stay informed and engaged.",
4	"Finding Coffee Spots: For your caffeine fix, cross the street to the café for artisan coffee.",
5	"Working Hours Flexibility: While our core hours are 9 AM to 5 PM, we offer flexibility to adjust as needed.",
6	]
7
8	# Embed the documents
9	doc_emb = co.embed(
10	model="embed-v4.0",
11	input_type="search_document",
12	texts=documents,
13	embedding_types=["float"],
14	).embeddings.float

1	# Add the user query
2	query = "Ways to connect with my teammates"
3
4	# Embed the query
5	query_emb = co.embed(
6	model="embed-v4.0",
7	input_type="search_query",
8	texts=[query],
9	embedding_types=["float"],
10	).embeddings.float

1	import numpy as np
2
3
4	# Compute dot product similarity and display results
5	def return_results(query_emb, doc_emb, documents):
6	n = 2 # customize your top N results
7	scores = np.dot(query_emb, np.transpose(doc_emb))[0]
8	max_idx = np.argsort(-scores)[:n]
9
10	for rank, idx in enumerate(max_idx):
11	print(f"Rank: {rank+1}")
12	print(f"Score: {scores[idx]}")
13	print(f"Document: {documents[idx]}\n")
14
15
16	return_results(query_emb, doc_emb, documents)

1	Rank: 1
2	Score: 0.262197161387274
3	Document: Joining Slack Channels: Be sure to join relevant channels to stay informed and engaged.
4
5	Rank: 2
6	Score: 0.1266074257723145
7	Document: Working Hours Flexibility: While our core hours are 9 AM to 5 PM, we offer flexibility to adjust as needed.

Setup

Cohere Platform

Private Deployment

Bedrock

SageMaker

Azure AI

Document Embeddings

Cohere Platform

Private Deployment

Bedrock

SageMaker

Azure AI

Query Embedding

Cohere Platform

Private Deployment

Bedrock

SageMaker

Azure AI

Semantic Search

Further Resources

Setup

Cohere Platform

Private Deployment

Bedrock

SageMaker

Azure AI

Document Embeddings

Cohere Platform

Private Deployment

Bedrock

SageMaker

Azure AI

Query Embedding

Cohere Platform

Private Deployment

Bedrock

SageMaker

Azure AI

Semantic Search

Further Resources