RAG and Embeddings
Build retrieval-augmented generation (RAG) pipelines and vector search systems with Parasail embeddings.
Build retrieval-augmented generation (RAG) pipelines, semantic search, and document similarity systems. Parasail supports leading open-source embedding models that rival proprietary alternatives.
Embedding models
GritLM
parasail-ai/GritLM-7B-vllm
Developed by Contextual, rivals proprietary models
GTE-Qwen2-7B-Instruct
Alibaba-NLP/gte-Qwen2-7B-instruct
From Alibaba, strong general-purpose embeddings
Any embedding model on Hugging Face can be used with a Dedicated Instance.
Generate embeddings
Serverless
from openai import OpenAI
client = OpenAI(
base_url="https://api.parasail.io/v1",
api_key="<PARASAIL_API_KEY>"
)
response = client.embeddings.create(
model="parasail-ai/GritLM-7B-vllm",
input="Parasail provides affordable cloud GPUs for AI inference.",
encoding_format="base64"
)
print(response.data[0].embedding[:5])Use encoding_format="base64" to reduce output sizes when you don't need floating-point arrays directly.
Relevant guides
RAG guide—step-by-step RAG implementation
Model selection—includes embedding model evaluation
API reference
Last updated