Class: Vectorsearch::Pinecone

Inherits:
Base
  • Object
show all
Defined in:
lib/vectorsearch/pinecone.rb

Constant Summary

Constants inherited from Base

Base::DEFAULT_COHERE_DIMENSION, Base::DEFAULT_METRIC, Base::DEFAULT_OPENAI_DIMENSION, Base::LLMS

Instance Attribute Summary

Attributes inherited from Base

#client, #index_name, #llm, #llm_api_key

Instance Method Summary collapse

Methods inherited from Base

#generate_completion, #generate_embedding, #generate_prompt

Constructor Details

#initialize(environment:, api_key:, index_name:, llm:, llm_api_key:) ⇒ Pinecone

Returns a new instance of Pinecone.



7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
 
# File 'lib/vectorsearch/pinecone.rb', line 7

def initialize(
  environment:,
  api_key:,
  index_name:,
  llm:,
  llm_api_key:
)
  ::Pinecone.configure do |config|
    config.api_key  = api_key
    config.environment = environment
  end

  @client = ::Pinecone::Client.new
  @index_name = index_name

  super(llm: llm, llm_api_key: llm_api_key)
end

Instance Method Details

#add_texts(texts:) ⇒ Hash

Add a list of texts to the index

Parameters:

  • texts (Array) —

    The list of texts to add

Returns:

  • (Hash) —

    The response from the server



28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
 
# File 'lib/vectorsearch/pinecone.rb', line 28

def add_texts(
  texts:
)
  vectors = texts.map do |text|
    {
      # TODO: Allows passing in your own IDs
      id: SecureRandom.uuid,
      metadata: { content: text },
      values: generate_embedding(text: text)
    }
  end

  index = client.index(index_name)

  index.upsert(vectors: vectors)
end

#ask(question:) ⇒ Object 



82
83
84
85
86
87
88
89
90
91
92
93
 
# File 'lib/vectorsearch/pinecone.rb', line 82

def ask(question:)
  search_results = similarity_search(query: question)

  context = search_results.dig("matches").map do |result|
    result.dig("metadata").to_s
  end
  context = context.join("\n---\n")

  prompt = generate_prompt(question: question, context: context)

  generate_completion(prompt: prompt)
end

#create_default_schema ⇒ Hash

Create the index with the default schema

Returns:

  • (Hash) —

    The response from the server



47
48
49
50
51
52
53
 
# File 'lib/vectorsearch/pinecone.rb', line 47

def create_default_schema
  client.create_index(
    metric: DEFAULT_METRIC,
    name: index_name,
    dimension: default_dimension
  )
end

#similarity_search(query:, k: 4) ⇒ Object 



55
56
57
58
59
60
61
62
63
64
65
 
# File 'lib/vectorsearch/pinecone.rb', line 55

def similarity_search(
  query:,
  k: 4
)
  embedding = generate_embedding(text: query)

  similarity_search_by_vector(
    embedding: embedding,
    k: k
  )
end

#similarity_search_by_vector(embedding:, k: 4) ⇒ Object 



67
68
69
70
71
72
73
74
75
76
77
78
79
80
 
# File 'lib/vectorsearch/pinecone.rb', line 67

def similarity_search_by_vector(
  embedding:,
  k: 4
)
  index = client.index(index_name)

  response = index.query(
    vector: embedding,
    top_k: k,
    include_values: true,
    include_metadata: true
  )
  response.dig("matches")
end