Intellectera

11 posts

Intellectera banner
Intellectera

Intellectera

@IntellecteraAI

Se unió Ocak 2024
9 Siguiendo7 Seguidores
Intellectera
Intellectera@IntellecteraAI·
next update is Dynamic Chart Generation thanks to @plotlygraphs ping us for demo🤟
English
0
0
1
109
Intellectera
Intellectera@IntellecteraAI·
@svpino we are doing this for you next update is dynamic chart generation pls check this video:
English
0
3
3
216
Santiago
Santiago@svpino·
This AI agent has left me wondering whether traditional RAG applications have a future besides simple use cases. PromptQL is a natural language API that executes Python and SQL-like queries on top of structured, unstructured, and any data behind an API. The most fascinating aspect of it is how it works: To answer a query, PromptQL creates an execution plan to access and operate the data it has access to. The best way to understand how this works is with an example. Imagine we write the following request: "Write an email to my latest customer describing the product they bought." The attached diagram shows every step that PromptQL will execute behind the scenes: 1. It will start by writing a SQL query to retrieve the latest customer from the database. 2. Using the customer ID, it will write a second SQL query to retrieve the list of products bought by this customer. 3. Using the list of products, it will retrieve their information from a vector store. 4. Finally, it will ask an LLM to write an email using the customer and the description of every product. PromptQL will automatically decide where to fetch each piece of information and will use Python to orchestrate the entire query plan. If it doesn't generate a good plan, you can nudge it in the right direction by improving the initial prompt. This is very impressive, especially compared to RAG applications, which are much less powerful and expressive than this. There are a few other characteristics that I'm excited to see in action: • PromptQL remembers previous interactions and uses this memory to solve complex workflows. • It has a high tolerance for failures and can automatically self-heal and improve the data it uses. • It can use any LLM, including your own. Here is much more information about PromptQL: shortclick.link/v9pbx7 Kudos to the team for all of their work and explanations. They are sponsoring this post. It's early, but I think agentic tools like PromptQL will become the main talking point of 2025.
Santiago tweet media
English
31
120
952
90.7K
Intellectera retuiteado
Rez
Rez@RezNetDevOps·
#رشتو ۱. شروع راه جدید و ریسکش نشونه اینه که هنوز زنده ایم🏃‍♂️ بعد از مدت ها جلو بردن اولین محصولمون @IntellecteraAI توی حوزه SaaS و Enterprise Solutions و اینکه دیگه به فاز بیشتر بیزینسی داستان برای فروش و فاندریز رسیدم ، با آرش @codewitharash تصمیم گرفتیم که …
فارسی
1
1
3
186
Intellectera
Intellectera@IntellecteraAI·
Create your AI Agent brain 🧠 Connect it to your database’s data 📊 Chat with your data or let customers Chat with their own data 💬
English
0
0
1
108
Intellectera
Intellectera@IntellecteraAI·
No more Query Just chat with your database💬 Our new feature is on the way: Database AI Agent 🧠 Stay tuned for new updates #intellectera
English
0
1
1
81
Intellectera
Intellectera@IntellecteraAI·
Intellectera can comprehend and be trained by your data in any format—text, tables, etc.—in a short amount of time, acting as a human endowed with your knowledge 📚. Thus, you can create a personalized 🧠 AI Agent that performs tasks as you instruct. #ai
English
1
2
3
213
Intellectera
Intellectera@IntellecteraAI·
Currently developing MVP. Feature list will be released soon 🚀 Stay tuned!
English
1
1
3
45
Intellectera
Intellectera@IntellecteraAI·
Intellectera, where innovation converges with intelligence. #AI
English
0
3
4
105