Ainsider #26

AI Video is entering into next phase

The Best custom AI Chatbots builders

Free Flowise RAG Chatbot template

AI Video is entering into next phase

1. Luma Labs after Dream Machine model dropped Keyframes features 🤯

Now you can create smooth and dynamic transitions between scenes (images) with outstanding quality of outputs

Keyframes are like the storyboard that helps the AI understand how to move from one point to another, which is necessary for #AI Video evolving into filmy fledged software 📹

2. Runway opened Gen-3 Alpha to Creative Partners Program.

Gen-3 Alpha can create highly detailed videos with complex scene changes, a wide range of cinematic choices, and detailed art directions.

3. Hedra: A New AI Tool for Creating Animated Videos with Talking Characters

Hedra is a new AI tool for creating animated videos with talking characters. The Character-1 model allows users to create animated videos with lip sync from a still image, adding expressive movements and greater levels of animation. It is currently free to use as part of a research preview, allowing users to experiment and help test the model and moderation tools. Despite a 30-second video limit and low resolution, Hedra is one of those rare things that makes me say "wow". Future plans include creating a fully controllable and realistic multimodal studio for characters capable of expressive dialogue, movement, etc.

The best platforms for building own #AI Chatbots and Assistants

In today’s rapidly evolving world of technology, AI chatbots are gaining popularity as effective tools for user interaction. Here’s an overview of the best applications and platforms for creating custom AI chatbots.

1. BOTPRESS
   Botpress is an open-source platform for building advanced AI assistants and chatbots, distinguished by its flexibility and a very wide range of functionalities – suitable for both coding and non-coding individuals.

Main features:

• Visual drag-and-drop workflow builder

• Built-in AI based on OpenAI API

• Support for multiple communication channels (website, Facebook, WhatsApp, etc.)

• Ability to train on your own data

• Integrations with popular tools (Zendesk, Zapier)

• Advanced AI capabilities: intents, entities, knowledge base

Url: https://botpress.com/

2. VOICEFLOW
   VoiceFlow is a modern and very powerful no-code platform for creating chatbots and assistants, including not only text-based messages but also voice assistants.

Key features:

• Intuitive drag-and-drop interface for designing conversations

• Creation of voice and text chatbots

• Integration with voice assistants (Alexa, Google Assistant)

• Advanced analytics and testing

• Real-time team collaboration

Url: https://www.voiceflow.com/

3. FLOWISE
   Flowise is a modern platform based on Langchain for creating chatbots, emphasizing access to advanced tools and process automation.

Flowise offers:

• No-code platform for building AI applications

• Visual flow editor

• Integration with various language models (GPT-3, BERT, etc.)

• Ability to create custom components

• Easy chatbot publishing and deployment

Url: https://flowiseai.com/

4. LANGFLOW
   LangFlow can be considered a simplified version of Flowise. LangFlow specializes in creating custom chatbots based on its own knowledge base.

Main features:

• Open-source tool for creating AI applications

• Drag-and-drop interface for connecting components

• Integration with popular AI libraries (Langchain, Hugging Face)

• Ability to export flows as Python code

• Support for various language models

Url: https://www.langflow.org/

5. CHATBASE
   Chatbase is an advanced platform for creating custom chatbots and AI assistants specifically designed for business needs.

Features:

• Quick creation of chatbots based on your own content

• Automatic response generation from documents

• Integration with popular platforms (Slack, Discord, websites)

• Advanced customization and branding capabilities

• Analytics and conversation tracking

Url: https://www.chatbase.co/

6. MANYCHAT
   ManyChat is a popular platform for creating chatbots for marketing and sales purposes.

Key features:

• Specialization in marketing and customer service chatbots

• Integration with Facebook Messenger and Instagram

• Advanced marketing automation features

• User segmentation and message personalization

• Tools for building mailing lists

Url: https://manychat.com/

7. GOOGLE DIALOGFLOW
   Google Dialogflow is a very powerful platform for creating conversational user interfaces based on artificial intelligence.

Main features:

• Advanced intent recognition

• Support for multiple languages and communication channels

• Integration with Google Cloud services

• Ability to create complex conversation scenarios

• Support for both voice assistants and text chatbots
  
  Url: https://cloud.google.com/dialogflow

Free Flowise RAG Chatbot template

In this guide, we will walk you through the process of creating an AI assistant chatflow in Flowise. This chatflow is designed to answer questions based on documents loaded into Pinecone, using various components integrated within Flowise.

Below is a step-by-step description of the setup, including the role and configuration of each block.

1. RECURSIVE CHARACTER TEXT SPLITTER

Purpose: The Recursive Character Text Splitter block is used to divide large documents into smaller chunks. This is essential for efficient processing and embedding generation.

Configuration:

• Chunk Size: 500 characters

• Chunk Overlap: 50 characters

• Additional Parameters: Default settings

The text splitter ensures that the text is broken down into manageable pieces, allowing for more accurate embeddings and retrievals later in the process.

2. CHEERIO WEB SCRAPER

Purpose: The Cheerio Web Scraper extracts content from a specified URL. This is particularly useful for dynamically fetching content from web pages.

Configuration:

• URL: The URL of the document you want to scrape (e.g., https://ainsider.notion.site/Ainsider-io)

• Text Splitter: Connects to the output of the Recursive Character Text Splitter

This block ensures that content from the specified web page is fetched and prepared for further processing.

3. PINECONE

Purpose: Pinecone is a vector database used to store and retrieve high-dimensional data, such as text embeddings.

Configuration:

• Document: Connects to the output of the Cheerio Web Scraper

• Embeddings: Takes embeddings generated from the OpenAI Embeddings block

• Record Manager: Default settings

• Pinecone Index: Specify the index (e.g., flowise.ainsiderbot)

Pinecone stores the document embeddings, allowing for efficient retrieval based on similarity searches.

4. OPENAI EMBEDDINGS

Purpose: This block generates embeddings for the chunks of text created by the text splitter.

Configuration:

• Connect Credential: Credential for FlowiseHuggingface1 (set up your OpenAI API key)

• Model Name: text-embedding-ada-002

Embeddings are vector representations of the text chunks, which capture semantic meaning and are used for similarity matching in Pinecone.

5. CHAT OPENAI

Purpose: This block serves as the interface for OpenAI’s chat model, which will generate responses based on user queries.

Configuration:

• Cache: Optional caching settings

• Connect Credential: Credential for FlowiseHuggingface1

• Model Name: gpt-3.5-turbo

• Temperature: 0.4 (controls the randomness of the output)

The ChatOpenAI block is responsible for formulating responses using the GPT-3.5-turbo model, guided by the context retrieved from Pinecone.

6. CONVERSATIONAL RETRIEVAL QA CHAIN

Purpose: The Conversational Retrieval QA Chain integrates all components to provide a final answer based on retrieved documents.

Configuration:

• Chat Model: Connects to the output of the ChatOpenAI block

• Vector Store Retriever: Connects to the output of the Pinecone Retriever

• Memory: Optional memory settings

• Input Moderation: Optional moderation settings

• Return Source Documents: Ensure this is enabled to provide context in responses

This block ties together the chat model and the vector store, ensuring that responses are grounded in the content of the documents stored in Pinecone.

SUMMARY

This chatflow setup in Flowise allows you to create an AI assistant capable of answering questions based solely on a predefined set of documents. By breaking down the document into smaller chunks, generating embeddings, storing them in Pinecone, and leveraging OpenAI’s GPT model for responses, you ensure accurate and contextually relevant answers.

Each block in this flow has a specific role, contributing to the overall functionality of the AI assistant. By following the configurations and connections as described, you can replicate this setup and adapt it to your own documents and use cases.

FREE FLOWISE CHATBOT TEMPLATE: