Text generation models are exceptional tools for both research purposes and applications. One of their strengths is their capabilities, which come from their architecture, training, and large datasets. These features shape how these models work.\u00a0<\/p>\n
TeapotAI\u2019s open-source model is a good example of a model that stands out with its work in TeapotLLM. This is a small language model<\/a> built on 800M parameters. It is also fine-tuned on synthetic data, allowing for efficiency in low-resource environments, including smartphones and CPUs. It is a great tool for various tasks. This model can perform only Q&A, RAG, and Information extraction within a given context.<\/p>\n This article was published as a part of the\u00a0<\/strong><\/em>Data Science Blogathon.<\/strong><\/em><\/a><\/p>\n TeapotLLM is a cutting-edge 800M parameter model with high accuracy. This small language model was built to generate hallucination-free information. It comes with its comprehensive Python<\/a> package, TeapotAI, that helps work with the model.\u00a0<\/p>\n This model builds on a transformer architecture and performs various natural language processing tasks. Developers fine-tuned it from flan-t5-base using a synthetic dataset of LLM tasks generated with Deepseek-V3.<\/p>\n There are several features of this model, including the following-<\/p>\n This model can be fine-tuned to perform retrieval augmented generation using the custom embedding model. The model can then learn to extract information from documents to answer questions.\u00a0<\/p>\n Teapot AI is trained to generate text within a provided context. This helps it avoid answering questions without sufficient data.\u00a0<\/p>\n This feature means that TeapotAI has a package that provides a pydantic-based data extraction function for the model. This permits you to get data from text efficiently and accurately.\u00a0<\/p>\n This model was built from fine-tuning Flan-T5-base and synthetic data. Its principles are based on a transformer model; Teapot AI is also built on the encoder-decoder architecture.\u00a0<\/p>\n Teapot LLM is a specialized language model fine-tuned from Flan-T5-Large, a well-known instruction-tuned variant of T5 (Text-To-Text Transfer Transformer). The base model, Flan-T5-Large, is a transformer-based architecture that excels at various natural language processing tasks by treating every problem as a text-to-text problem. Teapot LLM builds on this foundation and undergoes further refinement with a synthetic dataset of large language model<\/a> (LLM) tasks generated by DeepSeek-V3, an advanced generative model known for producing high-quality synthetic text. <\/p>\n The model\u2019s architecture uses the encoder-decoder structure popular with many transformer models to perform text generation. These two components all have their respective roles. The encoder processes input sequences, while the decoder does the same for output sequences.\u00a0<\/p>\n During processing, the encoder transforms the input text into a latent representation. The decoder, on the other hand, takes these representations and converts them into task-specific responses.\u00a0<\/p>\n This model\u2019s performance comes with a high contextual understanding. And it is easy to prove this from its architecture with certain standard transformer principles like the Transformer attention mechanism, incorporating multi-head self-attention layers, feed-forward networks, and layer normalization.\u00a0<\/p>\n This model can be used for various applications, such as answering questions, chatting with RAG, and extracting information. We\u2019ll explore the steps for running this model to perform these tasks.\u00a0<\/p>\n Firstly, you install the Python package needed for executing this task. This command installs TeapotAI with the functionalities required to carry out hallucination-resistant tasks.\u00a0\u00a0<\/p>\n This step requires you to import the TeapotAI class from the TeapotAI library. Importing this helps the model perform tasks like hallucination-resistant Q&A, Retrieval-Augmented Generation (RAG), and JSON extraction.<\/p>\n Providing context is another important step in running this model. This helps the model access information to perform the specified task.<\/p>\n This context usually comes in a multi-line string as shown above, with the information wrapped in the triple quotes.\u00a0<\/p>\n The code initializes Teapotai and uses it to request information based on the provided context mentioned earlier. To get the answer, we print (result) as shown below;<\/p>\n Here is a shot of the answer based on the context.\u00a0<\/p>\n Using this model as a chat when answering a question with many documents. Let\u2019s look at how we can run Teapot with this feature.<\/p>\n This code imports the necessary library just as with the first task.\u00a0<\/p>\n Here, can provide context that the RAG application will answer questions bases on; this could be long articles or a document. Below is a sample of this below;<\/p>\n This code defines a list named \u2018documents\u2019, where each element is a string containing factual information.<\/p>\n This initialization ensures that TeapotAI can use these documents for retrieval-augmented generation (RAG), answering questions based on the given information rather than generating responses from general knowledge.<\/p>\n This code uses TeapotAI\u2019s \u2018chat\u2019 method to generate a structured conversation and response. The input would be the message indicated in the \u201crole\u201d: \u201csystem\u201d and the \u201crole\u201d: \u201cuser\u201d fields. So, the answer will be based only on the given context of the list named \u2018documents\u2019 above.\u00a0\u00a0\u00a0<\/p>\n Here is the answer based on the documents.\u00a0<\/p>\n This model can extract information from context using JSON structures. The extract method uses a Pydantic model to guarantee that Teapot retrieves data in the correct format. It can infer fields based on their names and utilize descriptions when provided. This method seamlessly integrates with RAG and query functionalities for enhanced data extraction.<\/p>\n These libraries help validate data structures, such as the pydantic model. The BaseModel and Field are crucial to enforcing correct data formats. Together, they ensure accurate and structured information extraction from text.<\/p>\n Here, we provide the description from which we want to extract information: the details of an apartment.<\/p>\n Pets are welcome!<\/p>Learning Objectives\u00a0<\/h3>\n
\n
What is TeapotLLM?<\/h2>\n
Features of TeapotAI LLM<\/h2>\n
Retrieval Augmented Generation\u00a0<\/h3>\n
Hallucination Resistance<\/h3>\n
Model Architecture of Teapot LLM<\/h2>\n
![\"Model](\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/04\/Model-Architecture-of-Teapot-LLM.webp\")
![\"inputs](\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/04\/inputs-and-outputs.webp\")
How to Run Teapot LLM<\/h2>\n
Preparing the Environment<\/h3>\n
! pip install teapotai<\/code><\/pre>\nImporting Essential Library<\/h3>\n
from teapotai import TeapotAI<\/code><\/pre>\nContext<\/h3>\n
context = \"\"\"
Model Initialization and Query<\/h3>\n
teapot_ai = TeapotAI()\n\nanswer = teapot_ai.query(\n query=\"What is the height of the Eiffel Tower?\",\n context=context\n)<\/code><\/pre>\nprint (answer)<\/code><\/pre>\n![\"output\"](\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/04\/output-1.webp\")
<\/figure>\n from teapotai import TeapotAI<\/code><\/pre>\nContext<\/h3>\n
documents = [
Initializing Teapot With Documents for RAG<\/h3>\n
teapot_ai = TeapotAI(documents=documents)<\/code><\/pre>\nGetting the Answer Using RAG<\/h3>\n
answer = teapot_ai.chat([\n {\n \"role\":\"system\",\n \"content\": \"You are an agent designed to answer facts about famous landmarks.\"\n },\n {\n \"role\":\"user\",\n \"content\": \"What landmark was constructed in the 1800s?\"\n }\n])<\/code><\/pre>\nprint(answer)<\/code><\/pre>\n![\"TeapotLLM\"\/](\"https:\/\/av-eks-lekhak.s3.amazonaws.com\/media\/article_images\/Screenshot_2025-03-31_at_12.37.27.png\")
<\/figure>\nImporting Necessary Libraries<\/h3>\n
from teapotai import TeapotAI\nfrom pydantic import BaseModel, Field<\/code><\/pre>\nContext<\/h3>\n
apartment_description = \"\"\"
![\"result](\"https:\/\/cdn.analyticsvidhya.com\/wp-content\/uploads\/2025\/04\/result-of-teapot.webp\")
<\/figure>\n![\"Maigari](\"https:\/\/av-eks-lekhak.s3.amazonaws.com\/media\/lekhak-profile-images\/converted_image_9d7iCRC.webp\")
<\/p>\n