Post

More from @FlowiseAI

FlowiseAI

@FlowiseAI

Dec 23, 2024

They say you shouldn't push a new release right before the holidays...

So, here we go - v2.2.3 of Flowise 🎅

📈 Graph RAG using Neo4J
🗣️ Groq Whisper, Azure Cognitive Speech to Text
⚡ Composio Tools
💬 Deepseek Chat
📚 Epub document source

🧵

📈 Graph RAG using @neo4j

GraphRAG is a technique that enhances RAG with knowledge graphs.

Using Neo4J, we can easily create these graphs, and enabling structured and semi-structured information into the retrieval process.

🗣️ Groq Whisper, Azure Cognitive Speech to Text

More Speech to Text models added!

Read 7 tweets

FlowiseAI

@FlowiseAI

Aug 9, 2024

v2.0.4 release

🛝 Retrieval Playground
🔧 Ollama Tool Calling
📚 AWS Bedrock Knowledge Base
💰 GPT-4o snapshot

🧵:

🛝 Retrieval Playground

Figuring out better settings and strategy for your RAG application is hard.

With Playground, you can configure the upsert and retrieval settings, observe the results, and use it within your flow.

🔧 Ollama Tool Calling

Ollama supports tool calling not long ago. It's now supported on Flowise too!

ollama.com/blog/tool-supp…

Read 6 tweets

FlowiseAI

@FlowiseAI

Jul 24, 2024

This is the biggest update we've had in a while.

Flowise v2.0 and Flowise Cloud

With v2.0, we've introduced Sequential Agentic Workflow.

The new agentic workflow allows you to:
⛓️Chain agents together
🔁Loopback mechanisms
🙋Human-in-the-Loop
🔶Conditional branches

Different from existing chatflow which relies LLM to act on its own, now you have greater control over the flow. Huge shoutout to @LangChainAI team for the exceptional LangGraph framework, which made all of this possible!

We're also excited to announce the closed beta release of Flowise Cloud! In addition to all existing features, cloud version also includes Evals and Logging. Join the waitlist here:

Here's 7 examples to help you get started with agentic workflow:flowiseai.com/join

1/7 Agentic RAG

A self-improving RAG that checks the relevance of retrieved documents to the user's question.

If the documents are found to be irrelevant, the agent will rephrase the question and loop back to retrieve a new set of documents until they pass the relevance score.

2/7 Human in the Loop

Enable the agent to pause at specific stages and request human approval before continuing, which is useful for preventing the agent from autonomously executing sensitive operations.

Read 10 tweets

FlowiseAI

@FlowiseAI

Jun 22, 2023

Function usually takes in structured data. But it's hard to tell LLM to return structured data, until @OpenAI Function Calling.

In Flowise v1.2.13, we are introducing - Custom Tool ✨

Together with @LangChainAI agent, it will choose the right tool to call the function

🧵

🛠️ Custom Tool (1/2)

Create your own custom tool by specifying:
✅ Name
✅ Description
✅ Output Schema
✅ Function

🛠️ Custom Tool (2/2)

ChatGPT will decides:
🤔When to use the tool
🧱Return a structured data
⚡Call the function using the data

Result is way more reliable and way faster!

Here's an example of getting stock price movement and add it to @airtable inspired by @jasonzhou1993👇

Read 5 tweets

FlowiseAI

@FlowiseAI

May 23, 2023

🔍Metadata Filter is such an underrated topic.

When you have more vectors stored in vector database, it becomes harder to retrieve top relative vectors, resulting in irrelevant answer from LLM.

Watch how you can specify metadata to your documents and later filter by it 👇

With Flowise, you can specify a set of key-value pair as metadata to your document.

Most commonly used key value pairs are:
📚 document_id
🧑 user_id

The idea is to have a unique value for each document to better differentiate between them

When retrieving, you can then specify the metadata key-value pair.

This greatly increases the query flexibility, enabling much more advanced and targeted searches on your vector data ⚡

Read 4 tweets

FlowiseAI

@FlowiseAI

May 17, 2023

@AnthropicAI

🥷 We've gone stealth for the past 2 weeks. Now back with Flowise v1.2.6:

💬 Embedded Chat Widget
🔍 Metadata Filter
🌿 Support for AzureOpenAI, 100k-Claude @AnthropicAI models
⚡ Zapier NLA, WebBrowser tools
🔐 Apps authentication

🧵

💬 Embedded Chat Widget

Simply embed a chat widget to your websites that connects to your flow.

Watch how you can insert a link, and have a chat bot dedicated to answer question of the website 👇