Відео

Good comparison of two ways to build RAG applications. Good video...

Thank you for this video, it is really very informative and useful 😊

Thank you, very insightful. Pleased to have come across your channel.

🎯 Key Takeaways for quick navigation: 00:00 📋 *Introduction to Semantic Search and Comparison of Vector Stores* - Introduction to the video's topic: Semantic search and comparison of vector stores. - Explanation of the project "dry" aimed at creating a chatbot for repetitive questions. - Overview of how semantic search can solve the problem of repetitive queries. 02:00 🤖 *Understanding Semantic Search and Embeddings Models* - Explanation of semantic search and embeddings models. - Description of the OpenAI embeddings model (text embeddings ada002). - How embeddings models generate dense vectors for text strings. 05:24 🌲 *Pinecone: Fully Managed Vector Database* - Introduction to Pinecone as a fully managed vector database. - Setting up a Pinecone project and environment variables. - Demonstrating the integration with Pinecone for semantic search. 09:18 🌟 *Pinecone Efficiency, Effort, and Cost Evaluation* - Evaluation of Pinecone's efficiency for semantic search. - Discussion of the low effort required for integration with Pinecone. - Consideration of Pinecone's cost, especially for commercial projects. 20:06 🧊 *Facebook Faiss: Efficient Similarity Search* - Introduction to Facebook Faiss as an efficient similarity search library. - Setting up environment variables for Faiss and pidgey vector. - Integration of Faiss with the ability to store metadata. 26:30 ⚙️ *Faiss Efficiency, Effort, and Cost Evaluation* - Evaluation of Faiss's efficiency for semantic search. - Discussion of the initial integration effort and the need for metadata storage. - Consideration of costs associated with Faiss, including RAM requirements. 29:32 🐘 *PGVector: PostgreSQL Extension for Vector Search* - Introduction to PGVector as a PostgreSQL extension for vector search. - Overview of using PGVector to search by vectors in PostgreSQL. - Setting up PostgreSQL for PGVector integration. 29:44 🧩 *Setting Up Environment Variables and Database Connection* - Setting environment variables for API keys, connection string, similarity limit, and top K records. - Explanation of options to obtain a PostgreSQL database. - Introduction to using Superbase as an online service for PostgreSQL. 31:16 🧬 *Integration with OpenAI API and PostgreSQL Database* - Installation of the OpenAI package and confirmation of interaction with the OpenAI API. - Establishing a connection to the PostgreSQL database and creating a test table. - Installing the PGVector extension for PostgreSQL. 34:28 🛠️ *Generating Embeddings, Storing Data, and Testing Similarity Search* - Explanation of functions for generating embeddings, creating vector IDs, and storing data in the table. - Testing similarity search using cosine distance and filtering results. - Applying the "get similar and store" function to a list of test messages. 38:13 💼 *PGVector Efficiency, Effort, and Cost Evaluation* - Evaluation of PGVector's efficiency in the context of the project. - Discussion of the complexity of integration compared to Pinecone. - Consideration of cost implications, including using existing PostgreSQL databases and managed services. Made with HARPA AI

🎯 Key Takeaways for quick navigation: 00:00 🌐 *Overview of Semantic Search with OpenAI Embeddings* - Introduction to three setups for semantic search using OpenAI embeddings: Pinecone, FAISS, and pgvector. - Overview of the project "dry" aimed at solving repetitive questions in chatbots using semantic search. - Explanation of the schema, involving generating vectors, searching the vector database, and storing metadata for incoming messages. 02:26 🧠 *Understanding Semantic Search and Embeddings* - Definition of embeddings models, with a focus on OpenAI's text embeddings ada002. - Explanation of how embeddings models generate dense vectors representing words, sentences, or paragraphs. - Clarification of how the multi-dimensional space in the model reflects the semantic meaning of different strings. 05:24 🍍 *Pinecone Integration* - Introduction to Pinecone as a fully managed Vector database. - Demonstration of setting up a project, specifying environment variables, and creating a Pinecone index. - Implementation of Pinecone integration in a Google Colab notebook, including generating vectors, saving them, and performing similarity searches. 16:24 💲 *Evaluation of Pinecone* - Efficiency assessment of Pinecone as a managed service for vector storage. - Low effort needed for integration with Pinecone due to available Python and TypeScript examples. - Consideration of costs, with the expectation of a $70/month plan being sufficient for a pet project but potentially expensive for larger-scale commercial use. 18:23 📚 *FAISS Integration* - Introduction to FAISS as a library for efficient similarity search of dense vectors. - Noting nuances of FAISS, including the need to manage large indexes and separate metadata storage. - Implementation of FAISS integration in a Google Colab notebook, demonstrating vector generation, saving, and similarity searches. 28:23 💲 *Evaluation of FAISS* - Recognition of FAISS's efficiency in similarity search with proper usage and fine-tuning. - Intermediate effort level due to additional considerations for metadata storage and potential index management. - Acknowledgment of potentially lower costs as an open-source package but with considerations for high RAM requirements. 29:18 🐘 *pgvector Integration* - Introduction to pgvector as an extension for PostgreSQL, allowing searching by vectors. - Setting environment variables and connecting to a PostgreSQL database using Superbase. - Creation of a table with columns for vector ID, text, embeddings, and metadata, including dimensionality. 34:00 💲 *Evaluation of pgvector* - Recognition of pgvector's efficiency with potential for fine-tuning in usage. - Intermediate effort level, considering the need for an additional database for metadata storage. - Acknowledgment of potential costs, including high RAM requirements and potential additional expenses for hosting metadata. 34:15 📊 *pgvector Database Operations* - Introduction to functions for counting rows and deleting rows by ID in pgvector. - Demonstration of adding test messages to the table, generating embeddings, and saving vectors with metadata. - Usage of functions to search for top relevant messages based on cosine distance and manual filtering. 35:58 🧾 *Testing Similarity Search with pgvector* - Implementation and explanation of the get top relevant messages function in pgvector. - Testing similarity search on three test messages with varying relevance scores. - Display of results, showcasing the closest match with a similarity score of 0.106. 36:41 🔄 *Searching and Storing Similar Messages in pgvector* - Introduction to the gets similar and store function, aiming to search for similar messages and store new messages. - Execution of the function on a list of 91 messages from a Telegram chat. - Confirmation of matches found and the addition of new messages to the pgvector database. 38:13 💼 *Evaluation of pgvector* - Efficiency rating of pgvector with three stars, indicating its capability for the intended purpose. - Effort assessment, noting a moderate complexity in integration, especially for users familiar with SQL queries. - Consideration of potential costs, suggesting minimal impact if an existing PostgreSQL database is already part of the architecture. Made with HARPA AI

brother, this was really useful for me, i was about to do all this work and you did it for me. So thank you! so much

Can you do a video with FAISS and Any DB (Postgres)?

5:14 Pinecone 18:24 FIASS 29:17 pgvector

Very insightful for someone(me) new in this kind of GenAI applications. Thank you!

I wish you did not use langchain!

Great video thanks!

Quite useful and good comparison. It would have been easier to see using English sentences though. Well done!

QQ Doesn't using gdrive kind of defeat the object? Offline privacy....?

Добрий день! Дякую за дуже корисне та своєчасне відео. Маю питання, чи доцільно зберігати ембедінги в pgvector, а для similarity пошуку використовувати faiss?

Yes I was specifically thinking about chatbot response speed

My question = how to generate the same charrector over and over again doing different things but with same style

Which is fastest?

MongoDB and Qdrant would be great additions to this test :) Great video! Thanks

Great project. You should create more and open a private story book rentals business like my mummy new fun hobby project that she's WORKING ON and do kids story movie too.

You could actually use faiss.IndexFlatIP for cosine similarity

I am proficient in Python as **, * in BERT and *** in machine learning and *** in MarkdownV2

When using a hosted pgvector postgre service, would the cost be more like 2.5 stars?

Thank you for the great explanation. How does MongoDB fare in this regard?

Very helpful

Nice one mate. Just wish you did not use the russian text. As I do not understand russian, the results do not make any sense to me. But I am just believing... rather than knowing and seeing with my own eyes.

Браво! Крутий кейс! Єдиний момент - дракон схожий буде сильно на Беззубіка з мультфільму Діснея. Нейромережі у цьому сенсі небезпечна річ, комбінує готові рішення на основі захищенних авторським правом робіт.

You are a wonderful dad!👍👍👍

Thanks for a very concise and informative video!

Very useful. Thank you.

Beautiful project! My heart goes out to the people in Cherkasy ❤ I have a friend there 😊

Great video! You are so kind enough to share the contents of the book...pretty much everything. Wish you great success! Cheers.

Thx a lot, amazing video and great idea. Love it!

Hey! If you want to see some photos of the resulting printed book, please see the repository github.com/IuriiD/midjourneyKidsBook (added photos on July 02, 2023)

What pet did you get them in the end?🐶

Good luck selling any on Amazon along with the 33 million other titles you’re competing with? No one will ever find your book and I ought to know, I’ve published 8 kids books, never sold one!

Hello I am able to see the backend running after I input a query however I keep getting an unauthenticated error after the response is generated on the backend, it won’t send the intent to dialogue flow. Do you have idea how to fix this?

Thanks... Love your sharing

Thanks for sharing your ideas.

Thank you for the video. That's exactly what I was looking for.

This is great stuff. Thank you for such a detailed video highlighting all the 3 important aspects - embeddings, vectorDB and LLMs.

Good one, Iurii )

Nice video... I'm struggling with consistent characters. Do you have any tips/tricks or can you make a video about it? Thank you.

hi I'm curious if you plugged different models/ adjusted settings to get better answers and if you got your system to give you answers from the pdf

Great video I'm going to try it out but I have a question, why did you use all-mpnet-base-v2 instead of something more recent from sentence-transformers like all-MiniLM-L6-v2

There is a new model called LIMA that might be good for this.

Great thanks, how can I use it with my own data saved at txt file?

Юра, сделай видео на русском:)

Thank you for this very detailed and clear video

it gives me an error. it asks me to use oauth2 authentication? any solution?