AI & Machine Learning Solutions - Generative AI

Oodles’ Generative AI Development Solutions enable you to scale your professional capabilities, accelerate creative potential, and consistently deliver high-quality outcomes without compromise, empowering your business to stay ahead of the curve. Powered by advanced AI models such as Stable Diffusion, ChatGPT, and Llama, our custom solutions drive intelligent automation, enhance personalized content generation, and provide real-time data insights, helping you meet rising customer expectations in today’s increasingly demanding business ecosystem.

Resources

Opporture

Case Studies (5)

Opporture

Bedtime Stories

Shoorah | Mental Health Bot

RAG(Retrieval Augmented Generation) Bot

Bedtime Stories: Personalized Tales for Kids by Oodles AI

Solution Videos (1)

Lead the AI Frontier with Exponential Innovation | Custom Generative AI Development

Opporture

Case Studies (5)

Opporture

Bedtime Stories

Shoorah | Mental Health Bot

RAG(Retrieval Augmented Generation) Bot

Bedtime Stories: Personalized Tales for Kids by Oodles AI

Solution Videos (1)

Lead the AI Frontier with Exponential Innovation | Custom Generative AI Development

Top Blog Posts

Building a Chatbot with Mistral AI Step by Step Guide

Building a Chatbot with Mistral AI : Step by Step GuidePrerequisitesBefore we get started, you'll need to have the following:1. Basic understanding of JavaScript and Node.js.2. Node.js installed on your machine.3. Understand RESTful APIs.4. Access to Mistral AI API credentials.Step 1: Setting Up Your Node.js ProjectTo begin, create a new Node.js project. Navigate to your project directory in your terminal and run the following command:mkdir mistral-chatbot cd mistral-chatbot npm init -y This will create a new directory named mistral-chatbot and initialize a new Node.js project with the default settings.Step 2: Installing DependenciesNext, install the necessary dependencies that we'll need for our project. In this tutorial, we'll use Axios to make HTTP requests. Run the following command to install Axios:npm install axiosStep 3: Environment Setupa. Create a file named .env in the root of your project to store environment variables.b. Add the following variables to the .env file, replacing "MISTRAL_API_URL" and "YOUR_MISTRAL_API_KEY" with your actual Mistral API URL and API key, respectively MISTRAL_API_URL = MISTRAL_API_URL MISTRAL_API_KEY = YOUR_MISTRAL_API_KEY Step 4: Writing the Chatbot LogicNow, let's write the logic for our chatbot. Create a new file named chatbot.js in your project directory and add the following code:const MistralChatbot = async (req,res) => { try { let {message, mistralChatHistory, conversationId} = req.body; const history = JSON.parse(mistralChatHistory); const format = TEXT_RESPONSE_FORMAT; // if you want any type of formating in response , provide here // Append format to the last message in chat history history[history.length - 1].content += format; // Prepare data for Mistral API request const requestData = { model: 'mistral-tiny', messages: history, temperature: 0, }; // Send request to Mistral API const response = await axios.post(process.env.MISTRAL_API_URL, requestData, { headers: { 'Content-Type': 'application/json', 'Accept': 'application/json', 'Authorization': `Bearer ${process.env.MISTRAL_API_KEY}` } }); // Extract response from Mistral AI const data = response.data.choices[0].message.content; return res.status(200).json({success:true,data}); // Return response to the user } catch (error) { console.log(error); throw new Error('Failed to process message'); } }; module.exports = MistralChatbot;Step 5: Testing Your ChatbotYou can now test your chatbot by sending messages to your application and observing the responses generated by Mistral AI. Ensure that your Mistral API credentials are valid and that your application can communicate with the Mistral API endpoint.

Area Of Work:Chat bot, Generative AI

Industry:IT/Software

Mohd Ubaish

24 Feb 2024

Chat with your own Document using PrivateGPT

Chat with your own Document Using PrivateGPTPrivateGPT is a programme that allows you to ask questions about your documents without requiring an online connection, thanks to the power of Language Models. It is completely private, with no data leaving your execution environment at any stage. You can ingest documents and ask inquiries even without an internet connection!How privateGPT worksThis project is Divided intotwo phases1.)Ingest Phase (ingest.py file) , 2.)Query Phase(privateGPT.py file)Workings of Ingest Phase(ingest.py file)In our privateGPT project it takes the data from the source_document folder, split it into chunks and chunk overlaps by usingRecursiveCharacterTextSplitterclass.with the help of HuggingFaceEmbeddings(SentenceTransformers) and all-MiniLM-L6-v2 Model, it embedthe text.Embeddings are refers to the process of converting text or words into numerical representation (vectors) that can be understand and processed by machine learning algorithm. these text or words embeddings are essential for many Natural Language Processing tasks as they capture semantic relationships and contextual information between words, enabling machine to understand the meaning of the words and sentence in a numerical format.words with similar meanings or contexts are mapped closer together in the vector space. this allows machine learning models to leverage the similarities between words and make more informed decisions based on the context in which words appear.overall, text or word embeddings play a crucial role in bridging the gap between human language and machine learning algorithm, enabling computers to process and understand Natural language text more effectively.after creating the Embeddings we store into our Chroma DBChroma is a powerful toolset that allows developers to work with embeddings, store, index, and query these embeddings effectively and efficiently, and perform similarity searches on large-scale datasets.Working of Query Phase(privateGPT.py file)In this phase the user input serves as a query that is passed to the local Language Model (LLM) for processing and generating an answer. The LLM processes the query and produces an answer based on the context retrieved from the local vector database.User Input: The user provides a natural language text query, which serves as the input question.LLM Processing: The privateGPT.py script uses a local LLM (GPT4All-J or LlamaCpp) to process the user's question. The LLM has been pre-trained on a vast corpus of text and is capable of understanding Natural language and generating relevant responses.Context Retrieval: The script performs a similarity search using the local vector database (Chroma) to retrieve relevant context from the ingested documents by using RetrievalQA. The context consists of a selection of documents that are most similar to the user's query.Answer Generation: The LLM generates an answer based on the user's question and the context retrieved from the vector database. The LLM uses its language modeling capabilities to produce a response that fits the given context.Displaying the Answer: The script displays the answer generated by the LLM and presents the four sources (documents) used as context for generating that answer. This information helps the user understand how the LLM arrived at the response.SummaryIn summary, the user input is used as a query for the local LLM, and the LLM leverages the vector embeddings of the ingested documents (retrieved from the local vector database) to generate a relevant answer. The process does not directly create embeddings for the user input but rather uses embeddings of the documents to contextualize the LLM's response to the user's query.

Area Of Work:Chat bot, Generative AI

Ishandeep Singh

31 Jul 2023

Talk with your documents locally using langchain and llama 2

In recent years, the AI industry has grown significantly and is still growing rapidly day by day. Slowly it's becoming an integral part of our daily life, and giving rise to our productivity while cutting off the required time and effort. Whether we are cooking and need a professional instructor or to automate large machines in industries, your saviour AI is here.Suppose, you have an exam coming up in a week and you are still left with most of the topics to prepare or you just need to check your answer whether it's correct or not. Riffling through 100 and 1000 pages is clearly going to cost you your precious time, why not just ask the question to your book and it spits out the answer ? But that's impossible...Well, No! Not when AI is around.In a few minutes you will be able to do that. We will create an AI tool that will allow you to feed your document(s) and ask it questions.In this post, we hope to give you withA brief overview of Llama-2Brief overview of langchain.Brief of huggingFace.How to ingest your local document.Use Llama-2 to fetch answers from the uploaded documents.1. A brief overview of Llama-2:Llama 2 is an open source large language model (LLM) provided by Meta for research and commercial use.Llama 2 comes in three variants:Llama 2 7BLlama 2 13BLlama 2 70B2. Brief overview of langchain:Langchain is a software framework for large language models (LLMs) designed to simplify the creation of applications using AI and LLM.3. Brief of HuggingFace:HuggingFace is a platform where the machine learning community collaborates on models, datasets, and applications. We are using it to download theLlama-2 7b chat model.4. How to ingest your local document:The process of ingesting document involves following steps:Split Text into chunks:Chunking is the process of breaking large pieces of texts into smaller segments. # driver to create chunks of text and python file text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200) python_splitter = RecursiveCharacterTextSplitter.from_language( language=Language.PYTHON, chunk_size=880, chunk_overlap=200 ) # creating chunks of texts texts = text_splitter.split_documents(text_documents)Create embeddings:An embedding is a low-dimensional space that can be used to translate high-dimensional vectors.Ideally, an embedding captures some of the input's semantics by clustering semantically comparable inputs in the embedding space. Embeddings can be learned and reused across models. # Create embeddings embeddings = HuggingFaceInstructEmbeddings( model_name=EMBEDDING_MODEL_NAME, model_kwargs={"device": device_type},)Store the embeddings:we are using chromaDB to store the embeddings. db = Chroma.from_documents( texts, embeddings, persist_directory=PERSIST_DIRECTORY, client_settings=CHROMA_SETTINGS, )4. Use Llama 2 to fetch answer from your document:To QA with our document we have to follow these steps:Load the vectors:vectors are used to represent text or data in a numerical form that the model can understand and process. This representation is known as an embedding. # load the vectorstore db = Chroma( embedding_function=embeddings, persist_directory=PERSIST_DIRECTORY, ) retriever = db.as_retriever()Create Prompt Template: template = """Use the following pieces of context to answer the question at the end. If you don't know the answer,\ just say that you don't know, don't try to make up an answer. {context} {history} Question: {question} Helpful Answer:""" prompt = PromptTemplate( input_variables=["history", "context", "question"], template=template)Perform QA: qa = RetrievalQA.from_chain_type( llm=llm, chain_type="stuff", # chain_type="refine", retriever=retriever, return_source_documents=True, chain_type_kwargs={"prompt": prompt, "memory": memory}, ) To perform interactive QA, loop the process: # Interactive questions and answers while True: query = input("\nEnter a query: ") if query == "exit": break # Get the answer from the chain res = qa(query) answer, docs = res["result"], res["source_documents"] # Print the result print("\n\n> Question:") print(query) print("\n> Answer:") print(answer)Output:

Area Of Work:Generative AI

Industry:IT/Software