API векторизации текста

curl https://api.apiyi.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "input": "Artificial intelligence is changing the world",
    "model": "text-embedding-3-small"
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

def get_embedding(text, model="text-embedding-3-small"):
    """Get vector representation of text"""
    response = client.embeddings.create(
        input=text,
        model=model
    )
    return response.data[0].embedding

# Usage example
text = "Artificial intelligence is changing the world"
embedding = get_embedding(text)

print(f"Vector dimensions: {len(embedding)}")
print(f"First 5 values: {embedding[:5]}")

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

def batch_get_embeddings(texts, model="text-embedding-3-small"):
    """Batch get text vectors"""
    response = client.embeddings.create(
        input=texts,
        model=model
    )
    return [item.embedding for item in response.data]

# Batch processing
texts = [
    "Machine learning is the core technology of AI",
    "Deep learning drives the development of AI",
    "Natural language processing enables machines to understand human language",
    "Computer vision enables machines to see images"
]

embeddings = batch_get_embeddings(texts)
print(f"Successfully vectorized {len(embeddings)} texts")

import requests

def get_embedding_with_requests(text, model="text-embedding-3-small"):
    """Get vectors using requests library"""
    url = "https://api.apiyi.com/v1/embeddings"
    headers = {
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    }

    payload = {
        "model": model,
        "input": text
    }

    response = requests.post(url, headers=headers, json=payload)

    if response.status_code == 200:
        data = response.json()
        return data['data'][0]['embedding']
    else:
        print(f"Error: {response.status_code} - {response.text}")
        return None

# Usage example
embedding = get_embedding_with_requests("Artificial intelligence technology")
print(f"Vector dimensions: {len(embedding)}")

import numpy as np
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

def cosine_similarity(a, b):
    """Calculate cosine similarity"""
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

def semantic_search(query, documents, top_k=3):
    """Semantic search"""
    # Get query and document vectors
    all_texts = [query] + documents
    response = client.embeddings.create(
        input=all_texts,
        model="text-embedding-3-small"
    )

    embeddings = [item.embedding for item in response.data]
    query_embedding = embeddings[0]
    doc_embeddings = embeddings[1:]

    # Calculate similarity
    similarities = [
        cosine_similarity(query_embedding, doc_emb)
        for doc_emb in doc_embeddings
    ]

    # Sort and return most relevant documents
    ranked_indices = np.argsort(similarities)[::-1][:top_k]

    results = [
        {
            "document": documents[i],
            "similarity": similarities[i]
        }
        for i in ranked_indices
    ]

    return results

# Usage example
documents = [
    "Python is a high-level programming language",
    "Machine learning requires large amounts of data",
    "Deep learning is an important branch of AI",
    "JavaScript is used for web development"
]

query = "artificial intelligence and machine learning"
results = semantic_search(query, documents)

for i, result in enumerate(results, 1):
    print(f"{i}. {result['document']} (similarity: {result['similarity']:.4f})")

import numpy as np
import json
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

class SimpleVectorDB:
    """Simple vector database implementation"""

    def __init__(self, model="text-embedding-3-small"):
        self.model = model
        self.documents = []
        self.embeddings = []

    def add_documents(self, docs):
        """Add documents to vector database"""
        response = client.embeddings.create(
            input=docs,
            model=self.model
        )

        embeddings = [item.embedding for item in response.data]
        self.documents.extend(docs)
        self.embeddings.extend(embeddings)

        print(f"Added {len(docs)} documents to vector database")

    def search(self, query, top_k=5):
        """Search for most relevant documents"""
        response = client.embeddings.create(
            input=query,
            model=self.model
        )
        query_embedding = response.data[0].embedding

        # Calculate similarity
        similarities = []
        for doc_embedding in self.embeddings:
            sim = np.dot(query_embedding, doc_embedding) / (
                np.linalg.norm(query_embedding) * np.linalg.norm(doc_embedding)
            )
            similarities.append(sim)

        # Sort
        ranked_indices = np.argsort(similarities)[::-1][:top_k]

        return [
            {
                "document": self.documents[i],
                "similarity": similarities[i]
            }
            for i in ranked_indices
        ]

# Usage example
db = SimpleVectorDB()

# Add knowledge base documents
knowledge_base = [
    "Machine learning is a technology that enables computers to learn from data",
    "Deep learning uses multi-layer neural networks to process complex patterns",
    "Natural language processing helps computers understand human language",
    "Reinforcement learning trains agents through reward mechanisms"
]

db.add_documents(knowledge_base)

# Search
results = db.search("What is deep learning?", top_k=2)
for result in results:
    print(f"Similarity {result['similarity']:.4f}: {result['document']}")

from openai import OpenAI
import numpy as np

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.apiyi.com/v1"
)

class RAGSystem:
    """Simple RAG system implementation"""

    def __init__(self):
        self.knowledge_base = []
        self.embeddings = []

    def add_knowledge(self, documents):
        """Add knowledge to knowledge base"""
        response = client.embeddings.create(
            input=documents,
            model="text-embedding-3-small"
        )

        embeddings = [item.embedding for item in response.data]
        self.knowledge_base.extend(documents)
        self.embeddings.extend(embeddings)

    def retrieve(self, query, top_k=3):
        """Retrieve relevant documents"""
        response = client.embeddings.create(
            input=query,
            model="text-embedding-3-small"
        )
        query_embedding = response.data[0].embedding

        # Calculate similarity
        similarities = [
            np.dot(query_embedding, doc_emb) / (
                np.linalg.norm(query_embedding) * np.linalg.norm(doc_emb)
            )
            for doc_emb in self.embeddings
        ]

        # Get most relevant documents
        top_indices = np.argsort(similarities)[::-1][:top_k]
        return [self.knowledge_base[i] for i in top_indices]

    def generate_answer(self, question):
        """Generate answer"""
        relevant_docs = self.retrieve(question, top_k=3)

        context = "\n".join(relevant_docs)
        prompt = f"""Answer the question based on the following knowledge:

Knowledge base content:
{context}

Question: {question}

Please provide an accurate answer based on the above knowledge:"""

        response = client.chat.completions.create(
            model="gpt-4o-mini",
            messages=[
                {"role": "user", "content": prompt}
            ],
            temperature=0.3
        )

        return response.choices[0].message.content

# Usage example
rag = RAGSystem()

knowledge = [
    "GPT-4 is a large language model developed by OpenAI with powerful understanding and generation capabilities.",
    "Claude is an AI assistant developed by Anthropic, focusing on safety and helpfulness.",
    "Gemini is a multimodal AI model developed by Google, supporting text, images, and video.",
    "LLaMA is an open-source large language model series developed by Meta."
]

rag.add_knowledge(knowledge)

question = "Who developed GPT-4?"
answer = rag.generate_answer(question)
print(f"Question: {question}")
print(f"Answer: {answer}")

import re

def preprocess_text(text):
    """Text preprocessing"""
    text = re.sub(r'\s+', ' ', text)
    return text.strip()

def chunk_text(text, max_tokens=500, overlap=50):
    """Split long text into chunks"""
    words = text.split()
    chunks = []

    for i in range(0, len(words), max_tokens - overlap):
        chunk = ' '.join(words[i:i + max_tokens])
        chunks.append(chunk)

    return chunks

import hashlib
import pickle
import os

class EmbeddingCache:
    """Vector caching system"""

    def __init__(self, cache_dir="./embedding_cache"):
        self.cache_dir = cache_dir
        os.makedirs(cache_dir, exist_ok=True)

    def _get_cache_key(self, text, model):
        """Generate cache key"""
        content = f"{text}_{model}"
        return hashlib.md5(content.encode()).hexdigest()

    def get(self, text, model):
        """Get cached vector"""
        cache_key = self._get_cache_key(text, model)
        cache_file = os.path.join(self.cache_dir, f"{cache_key}.pkl")

        if os.path.exists(cache_file):
            with open(cache_file, 'rb') as f:
                return pickle.load(f)
        return None

    def set(self, text, model, embedding):
        """Save vector to cache"""
        cache_key = self._get_cache_key(text, model)
        cache_file = os.path.join(self.cache_dir, f"{cache_key}.pkl")

        with open(cache_file, 'wb') as f:
            pickle.dump(embedding, f)

import time
from openai import OpenAI

def get_embedding_with_retry(text, model="text-embedding-3-small", max_retries=3):
    """Get vector with retry mechanism"""
    client = OpenAI(
        api_key="YOUR_API_KEY",
        base_url="https://api.apiyi.com/v1"
    )

    for attempt in range(max_retries):
        try:
            response = client.embeddings.create(
                input=text,
                model=model
            )
            return response.data[0].embedding

        except Exception as e:
            print(f"Attempt {attempt + 1}/{max_retries} failed: {e}")
            if attempt < max_retries - 1:
                time.sleep(2 ** attempt)
            else:
                raise

    return None