Tune Assistant Makes LLM Smarter
by 🎙️ @aakash7539 & @priyas- 🧑🏻💻 Software Engineer at Tune AI
- 🏗️ Building GenAI, ML Systems, and Infra at Tune
-
@aakash7539
About Aakash
About Priya
- 🧑🏻💻 Software Engineer at Tune AI
- 🏗️ Been building Assistants, Backend System and Product
-
@priyas
A tech startup with roots in the city of Chennai. Currently in San Francisco, Bangalore and Chennai. We want to build the best AI out there.
We are the fastest at deploying Llamas in the world. We put Llama-2 in 24 hours and Llama-3 in 1 hour from launch!
We have built two products, called Tune Studio and Tune Chat.
999,999,999…
Tokens Generated
6,768,000+
Over 6.5 Million conversations with AIs that can read files, generate images, send emails, surf internet and more.
431,300+
Signups on Tune AI
Why is a basic LLMs not smart
- Limited to generating text based on patterns learned from its training data.
- Cannot handle more complex conversations, such as booking a flight or making a payment
- Cannot provide real-time updates, such as fetching the latest news or weather updates
-
Glorified Text Generation Model
Assistants is the solution
-
Solve Complex, Multi-step tasks
-
Proactive vs. Reactive
(Agents vs. ChatGPT)
-
24/7 Operation vs. Single-interaction model
*Email*
follow this thread
*Analyst*
Hey, i found the
discrepancies
-
"Just a software" that uses A.I. to accomplish tasks.
-
Executes multiple steps.
-
Steps are determined by an LLM.
-
Sometimes, the “orchestration layer” is needed.
What ❓
“A person's a person, no matter how small.”
― Dr. Seuss
Agentic Workflow
- Sophisticated iterative and multi-step process to interact and instruct LLMs to complete complex tasks with more/better accuracy.
- In this process, a single task is divided into multiple small tasks that are more manageable
- And each task leave scope for improvements throughout the task completion process.
Multi agent framework in a nutshell
-
Proactive Not Reactive
-
Non-stop (Internal monologue)
-
Commodities Tools
What Tune thinks Agents should be
Internet Search 🔍
- SerpAPi
- Exa.ai
- anon.com
Maps 🗺️📍
- Google Maps
- OSM
Documents 📃
- Google Docs
- Notion
Key Components 🏗️⚙️
-
Function-calling LLM 🧠
-
Task schedulers and orchestrators 🤹🏻♂️
-
Tool integration for expanded capabilities 🛠️
Call LLM with Tools
LLM responds function
You run function
LLM gives response
Allows access to application logic and data directly through the chat completion API.
Enhances the LLM's ability to provide accurate and relevant responses.
Identifies the function using its description from the list of available tools
Provides the function name and needed arguments in a JSON response.
You call the required function with the provided arguments.
Ensures the correct data or action is retrieved or completed
LLM uses the results from the function to generate a response.
Response is detailed and tailored to the user's query.
Function Calling Flow
Function calling Flow
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Proin urna odio, aliquam vulputate faucibus id, elementum lobortis felis. Mauris urna dolor, placerat ac sagittis quis.
Title Text
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Proin urna odio, aliquam vulputate faucibus id, elementum lobortis felis. Mauris urna dolor, placerat ac sagittis quis.
Behind the scenes - Function Calling Process Flow
Tune Assistant Design
Limitations
-
Models are "stupiddd"
- Recursive multistep sucks
- Hallucination with scaling functions
- Baby level understanding of complex functions - data problem
- Massive models
-
LLMs are not fast (Not enough tokens/sec)
- Agents Thinking
- Thinking Tokens
- Less Tokens Less thinking/sec
- Less thinking/sec Slow agents
Checkout the more samples 👇
Text
Subscribe to our newsletter for the latest in GenAI news and updates 📰 🤓
tune.beehiiv.comThank You!!
