1
# pip install cohere
2
3
import cohere
4
import numpy as np
5
6
# Get your free API key: https://dashboard.cohere.com/api-keys
7
co = cohere.ClientV2(api_key="COHERE_API_KEY")

1
# Define the documents
2
faqs_long = [
3
    {
4
        "text": "Joining Slack Channels: You will receive an invite via email. Be sure to join relevant channels to stay informed and engaged."
5
    },
6
    {
7
        "text": "Finding Coffee Spots: For your caffeine fix, head to the break room's coffee machine or cross the street to the café for artisan coffee."
8
    },
9
    {
10
        "text": "Team-Building Activities: We foster team spirit with monthly outings and weekly game nights. Feel free to suggest new activity ideas anytime!"
11
    },
12
    {
13
        "text": "Working Hours Flexibility: We prioritize work-life balance. While our core hours are 9 AM to 5 PM, we offer flexibility to adjust as needed."
14
    },
15
    {
16
        "text": "Side Projects Policy: We encourage you to pursue your passions. Just be mindful of any potential conflicts of interest with our business."
17
    },
18
    {
19
        "text": "Reimbursing Travel Expenses: Easily manage your travel expenses by submitting them through our finance tool. Approvals are prompt and straightforward."
20
    },
21
    {
22
        "text": "Working from Abroad: Working remotely from another country is possible. Simply coordinate with your manager and ensure your availability during core hours."
23
    },
24
    {
25
        "text": "Health and Wellness Benefits: We care about your well-being and offer gym memberships, on-site yoga classes, and comprehensive health insurance."
26
    },
27
    {
28
        "text": "Performance Reviews Frequency: We conduct informal check-ins every quarter and formal performance reviews twice a year."
29
    },
30
    {
31
        "text": "Proposing New Ideas: Innovation is welcomed! Share your brilliant ideas at our weekly team meetings or directly with your team lead."
32
    },
33
]
34
35
# Embed the documents
36
doc_emb = co.embed(
37
    model="embed-v4.0",
38
    input_type="search_document",
39
    texts=[doc["text"] for doc in documents],
40
).embeddings

1
# Add the user query
2
query = "How do I stay connected to what's happening at the company?"
3
4
# Embed the query
5
query_emb = co.embed(
6
    model="embed-v4.0",
7
    input_type="search_query",
8
    texts=[query],
9
).embeddings

1
# Compute dot product similarity and display results
2
def return_results(query_emb, doc_emb, documents):
3
    n = 2
4
    scores = np.dot(query_emb, np.transpose(doc_emb))[0]
5
    scores_sorted = sorted(
6
        enumerate(scores), key=lambda x: x[1], reverse=True
7
    )[:n]
8
9
    for idx, item in enumerate(scores_sorted):
10
        print(f"Rank: {idx+1}")
11
        print(f"Score: {item[1]}")
12
        print(f"Document: {documents[item[0]]}\n")
13
14
15
return_results(query_emb, doc_emb, documents)

1
# Define the documents
2
faqs_short_fr = [
3
    {
4
        "text": "Remboursement des frais de voyage : Gérez facilement vos frais de voyage en les soumettant via notre outil financier. Les approbations sont rapides et simples."
5
    },
6
    {
7
        "text": "Travailler de l'étranger : Il est possible de travailler à distance depuis un autre pays. Il suffit de coordonner avec votre responsable et de vous assurer d'être disponible pendant les heures de travail."
8
    },
9
    {
10
        "text": "Avantages pour la santé et le bien-être : Nous nous soucions de votre bien-être et proposons des adhésions à des salles de sport, des cours de yoga sur site et une assurance santé complète."
11
    },
12
    {
13
        "text": "Fréquence des évaluations de performance : Nous organisons des bilans informels tous les trimestres et des évaluations formelles deux fois par an."
14
    },
15
]
16
17
documents = faqs_short_fr
18
19
# Embed the documents
20
doc_emb = co.embed(
21
    model="embed-v4.0",
22
    input_type="search_document",
23
    texts=[doc["text"] for doc in documents],
24
).embeddings
25
26
# Add the user query
27
query = "What's your remote-working policy?"
28
29
# Embed the query
30
query_emb = co.embed(
31
    model="embed-v4.0",
32
    input_type="search_query",
33
    texts=[query],
34
).embeddings
35
36
# Compute dot product similarity and display results
37
return_results(query_emb, doc_emb, documents)

1
# Define the documents
2
documents = faqs_long
3
4
# Embed the documents with the given embedding types
5
doc_emb = co.embed(
6
    model="embed-v4.0",
7
    embedding_types=["float", "int8"],
8
    input_type="search_document",
9
    texts=[doc["text"] for doc in documents],
10
).embeddings
11
12
# Add the user query
13
query = "How do I stay connected to what's happening at the company?"
14
15
# Embed the query
16
query_emb = co.embed(
17
    model="embed-v4.0",
18
    embedding_types=["float", "int8"],
19
    input_type="search_query",
20
    texts=[query],
21
).embeddings

1
# Compute dot product similarity and display results
2
return_results(query_emb.float, doc_emb.float, faqs_long)

1
# Compute dot product similarity and display results
2
return_results(query_emb.int8, doc_emb.int8, documents)