Recommended Models
ServerAssistantAI supports a wide range of language models from different providers, including premium and free options, allowing server owners to choose the model that best fits their needs. Here's what we recommend, listed from most recommended to least.
Embedding Models
Embedding models are used to convert text data into numerical representations called embeddings. These embeddings capture the semantic meaning and relationships between different pieces of text, allowing the AI to find the most relevant context from the document.txt file when answering a question.
| Provider | Embedding Model | Pricing | Description |
|---|---|---|---|
Paid | OpenAI's large embedding model for text similarity and retrieval tasks. | ||
Free & Paid | English embedding model great for noisy data, enabling better retrievals for RAG. | ||
Free & Paid | Multilingual embedding model great for noisy data, enabling better retrievals for RAG. | ||
Paid | OpenAI's small embedding model for text similarity and retrieval tasks. |
ServerAssistantAI only sends information to the embedding API when changes are made to the document.txt file. If no changes are detected, the plugin will use the previously cached embeddings to reduce API calls.
Large Language Models
Large Language Models (LLMs) are powerful AI models that can understand and generate human-like text based on the input they receive. In ServerAssistantAI, LLMs process the user's question along with the relevant context provided by the embedding model to generate accurate and context-aware responses.
| Provider | Large Language Model | Pricing | Description |
|---|---|---|---|
Paid | OpenAI's most advanced model. Same intelligence as GPT-4 Turbo but 2x faster and 50% cheaper. | ||
Free & Paid | Gemini 1.5 Pro offers long-context understanding, with a context window of up to 1 million tokens. | ||
Paid | OpenAI's GPT-4-Turbo model with 128K context, newer knowledge and more powerful than GPT-4. | ||
Free & Paid | Gemini 1.5 Flash has higher rate limits than Gemini 1.5 Pro and is Google's fastest, most cost-efficient model. | ||
Paid | Anthropic's most intelligent model with great performance on highly complex tasks. | ||
Temporarily Free | Meta's Llama 3 70B instruction-tuned model which outperforms almost all open-source chat models and using Groq, the inference speed is 300+ Tokens per second! | ||
Paid | Claude 3 Sonnet balances intelligence and speed, ideal for enterprise workloads. | ||
Free & Paid | Advanced RAG model with 128k context, multilingual support, and tool use capabilities. | ||
Paid | Claude 3 Haiku is Anthropic's fastest model for near-instant responsiveness. | ||
Free & Paid | Scalable generative model for RAG and Tool Use in enterprise applications. | ||
meta-llama/Meta-Llama-3-8B-Instruct | Free | Meta's Llama 3 8B instruction-tuned model and outperforming many open-source chat models. | |
01-ai/Yi-1.5-34B-Chat | Free | 01.AI's Yi-1.5 model, offering strong performance in coding, math, reasoning, and instruction-following. | |
mistralai/Mixtral-8x7B-Instruct-v0.1 | Free | Mistral AI's 8x7B instruction-following model, version 0.1. | |
Paid | OpenAI's GPT-3.5 model with a larger context size of 16K tokens. |
All Large Language Models and Embedding Models from the HuggingFace Inference API are completely free to use!
Please note that each model may have specific requirements or considerations for optimal performance. When selecting a model, consider factors such as:
System prompt configuration: Different models may require adjustments to the system prompt to achieve the best results. Check the documentation provided by the model's creators for tips on prompt engineering and configuration.
Open-source free LLMs have a higher chance of hallucinating compared to paid models.
Last updated