Together AI チュートリアル: 基礎から高度なRAGまで

# Uncomment the following line to install the required packages
# %pip install together python-dotenv numpy

import os
from dotenv import load_dotenv
import together

load_dotenv()

client = together.Together(api_key=os.environ.get("TOGETHER_API_KEY"))

knowledge_base_content = """
Together AI offers a cloud platform for building and running generative AI. It provides access to over 100 open-source models.
The platform is designed for high-performance inference, leveraging techniques like speculative decoding.
For Retrieval-Augmented Generation, Together AI offers both embedding models and reranker models.
The BAAI/bge-large-en-v1.5 is a popular and powerful model for generating text embeddings.
Reranking is a crucial step in a RAG pipeline to improve the quality of retrieved documents before sending them to the language model.
The Together AI Python client is compatible with the OpenAI API, making it easy for developers to switch.
Users can fine-tune models on their own data to create specialized, expert models.
Together AI offers both serverless, pay-as-you-go endpoints and dedicated instances for large-scale applications.
"""

with open("knowledge_base.txt", "w") as f:
    f.write(knowledge_base_content)

# Now, we'll load the text and split it into chunks (in this case, by line).
with open("knowledge_base.txt", "r") as f:
    knowledge_base = [line.strip() for line in f.readlines() if line.strip()]

embedding_model = "BAAI/bge-large-en-v1.5"

embeddings_response = client.embeddings.create(
    model=embedding_model,
    input=knowledge_base,
)

document_embeddings = [embedding.embedding for embedding in embeddings_response.data]

import numpy as np
from numpy.linalg import norm

def cosine_similarity(a, b):
    return np.dot(a, b) / (norm(a) * norm(b))

user_query = "How can I improve my RAG system?"
top_k = 3

query_embedding_response = client.embeddings.create(
    model=embedding_model,
    input=[user_query],
)
query_embedding = query_embedding_response.data[0].embedding

similarities = [cosine_similarity(query_embedding, doc_embedding) for doc_embedding in document_embeddings]

top_indices = np.argsort(similarities)[-top_k:][::-1]
retrieved_documents = [knowledge_base[i] for i in top_indices]

print("Retrieved documents (before reranking):")
for doc in retrieved_documents:
    print(f"- {doc}")

rerank_model = "mixedbread-ai/Mxbai-Rerank-Large-V2"

rerank_response = client.rerank.create(
    model=rerank_model,
    query=user_query,
    documents=retrieved_documents,
)

reranked_indices = [result.index for result in rerank_response.results]
reranked_documents = [retrieved_documents[i] for i in reranked_indices]

print("\nReranked documents:")
for doc in reranked_documents:
    print(f"- {doc}")

context = reranked_documents[0] # Use the top reranked document

prompt = f"""
Context: {context}
Question: {user_query}
Based on the provided context, give a concise answer.
Answer:
"""

response = client.chat.completions.create(
    model="meta-llama/Llama-3-8b-chat-hf",
    messages=[{"role": "user", "content": prompt}],
    temperature=0.7,
)

print(f"\nFinal Answer:\n{response.choices[0].message.content}")