[-0.015128633938729763, 6.5704266489774454e-06, 0.013684336096048355, 0.000725181307643652, 0.0792837142944336, 0.02489437721669674, 0.04961267486214638, 0.04444398730993271, -0.0032522594556212425, -0.07948382198810577, ...]

• First, embeddings are not exclusive to text, it’s also possible to generate them for images, audio, etc.
• Second, embeddings are generated by Machine Learning models, and each model will generate different embeddings.
• Third, there are specialized models for generating embeddings (freely available & from OpenAI).
• Fourth, generating embeddings using these models is way cheaper than generating text completions (like GPT).

# Step 1: Import necessary libraries
from flask import Flask, jsonify, request
from sentence_transformers import SentenceTransformer
# Step 2: Create a Flask application
app = Flask(__name__)
# Step 3: Define your function
def get_embeddings(data): sentences = data model = SentenceTransformer('thenlper/gte-base') embeddings = model.encode(sentences)
return embeddings
# Step 4: Create an API endpoint
@app.route('/get_embeddings', methods=['POST'])
def api_call_function():
# Get 'data' from query string
result = get_embeddings(request.form.getlist('data'))
# Return the result as JSON
return jsonify({"embeddings": result.tolist()})
# Step 5: Run the flask application locally
if __name__ == '__main__':
app.run(debug=True)

require 'json'
require 'excon'

EMBEDDINGS_API_URL = "http://localhost:5000/get_embeddings"

class SentenceTransformer
  def self.get_embeddings_from_model(data)
    JSON.parse(
      Excon.post(
        EMBEDDINGS_API_URL,
        body: URI.encode_www_form({data: data}),
        headers: { "Content-Type" => "application/x-www-form-urlencoded" }
      ).body
    ).dig("embeddings")
  end
end

data = ARGV[0..]

vectors = SentenceTransformer.get_embeddings_from_model(data)

# Array of vector embeddings
p vectors

# How many vectors we are getting back
p vectors.size

# Size of an individual vector
p vectors.first.size 

The 1st time you try to fetch your embeddings the Python code will download the ML model from huggingface.co, this particular model thenlper/gte-base, requires about 300 MB of disk space. Other models, such as those for creating a chat experience or images, can be much larger (>= 3 GB).

require 'chroma-db'
require 'logger'
require 'digest'

Chroma.connect_host = "http://localhost:8000"
Chroma.logger       = Logger.new($stdout)
Chroma.log_level     = Chroma::LEVEL_ERROR

# Check current Chrome server version
version = Chroma::Resources::Database.version
puts "Connected to DB: v #{version}"

# Create a collection, this is like a new table on SQL

collection = Chroma::Resources::Collection.create(collection_name, { lang: "ruby", gem: "chroma-db" })

document = ARGV[0]
vectors  = SentenceTransformer.get_embeddings_from_model(document)

# MD5 digest is used here to create unique IDs, but you can use any kind of id-generation scheme that you like, as long as they are unique for each embedding

# Inside the metadata key you can include any info that you find convenient, it's often useful to include the source of your data, specially if you're sourcing from multiple documents

vectors.each do |vector|
    collection.add(
        Chroma::Resources::Embedding.new(
          id: Digest::MD5.hexdigest(document),
          embedding: vector,
          document: doc,
          metadata: { source: EMBEDDINGS_SOURCE }
        )
    )
end

# I added a whole free book on statistics to my Chroma Db, this is my example query
query = "how to calculate Z value for normals"

# Just one result as an example, but you should try 3-4 results
results = collection.query(
    query_embeddings: SentenceTransformer.get_embeddings_from_model(query),
    results: 1
)

pp results

 [#<Chroma::Resources::Embedding:0x00007f4480c8cb40
  @distance=0.23495814204216003,
  @document=
   "Statistical software can also be used. A normal probability table is given in Appendix B.1 on page 427 and abbreviated in Table 3.8. We use this table to identify the percentile corresponding to any particular Z-score. For instance, the percentile of Z = 0.43 is shown in row 0.4 and column 0.03 in Table 3.8: 0.6664, or the 66.64th percentile",
  @embedding=nil,
  @id="7074239f7a4801fad16e30a8ca1b300e",
  @metadata={"source"=>"Intro to Stats 3ed"}>]

• The vector database takes embeddings for its query because it compares embeddings with embeddings using math, specifically, it’s using a “similarity function”, one such F(x) is “cosine similarity”.
• Try querying for the same word, for example, if you added “chocolate” search for “chocolate”, then “dessert”, and “person”, to see the differences in the distance value.

require 'baran'

CHUNK_SIZE = 512
OVERLAP_PERCENT = 0.25

splitter = Baran::RecursiveCharacterTextSplitter.new(
    chunk_size: CHUNK_SIZE,
    chunk_overlap: CHUNK_SIZE * OVERLAP_PERCENT,
    separators: ["\n\n", "\n", ".", ","]
)

# This is your question, it can be the same one you searched for on Chroma
question = "..."

# This is the joined chunks from Chroma DB
context  = "..."

chat_prompt = "Answer the following user question using ONLY the given context, never mention the context, just answer the question. Question: #{question}. Context: #{context}"

require 'openai'

client = OpenAI::Client.new(access_token: <your API key>)

response = CLIENT.chat(
    parameters: {
        model: "gpt-3.5-turbo",
        messages: [
            { role: "user", content: chat_prompt }
        ]
    }
)

if response.key?("error")
    puts "Error: #{response}"
else
    puts response.dig("choices", 0, "message", "content")
end