Mattingly "Text and Data Mining: Searching Vectors"
0 likes312 views
The document discusses various topics related to text and data mining, including named entity recognition (NER), vector databases, multi-modal data mining, and retrieval-augmented generation (RAG). It explains the classification of entities, methods for extracting information, and the advantages of using vector databases for similarity searches. Additionally, it describes how RAG combines large language models with vector databases to improve query relevance and reduce misinformation.
![Representing
Texts
Digitally
Bag-of-Words
● The apple is in the tree.
○ 1-the
○ 2-apple
○ 3-is
○ 4-in
○ 1-the
○ 5-tree
● [1, 2, 3, 4, 1, 5]](https://image.slidesharecdn.com/niso07-introductiontotextanddatamining-231205201913-0e562fef/85/Mattingly-Text-and-Data-Mining-Searching-Vectors-12-320.jpg)
![Representing
Texts
Digitally
Embeddings
● The apple is in the tree.
○ 1-[0.01234, -0.23456, 0.87654,
0.45678, -0.56123, 0.65432,
0.12345, -0.77123, 0.08456,
0.34567, ...]
○ 2-different vector
○ 3-different vector
○ 4-different vector
○ 1-[0.01234, -0.23456, 0.87654,
0.45678, -0.56123, 0.65432,
0.12345, -0.77123, 0.08456,
0.34567, ...]
○ 5-different vector](https://image.slidesharecdn.com/niso07-introductiontotextanddatamining-231205201913-0e562fef/85/Mattingly-Text-and-Data-Mining-Searching-Vectors-13-320.jpg)
Mattingly "Text and Data Mining: Searching Vectors"
- 1. Text and Data Mining Searching Vectors
- 2. 1. Named Entity Recognition - Deeper Dive 2. Semantic Searching as a Concept 3. Vector Databases 4. Semantic Searching 5. Multi-Modal Data Mining 6. Retrieval-Augmented Generation (RAG) Goals
- 3. Named Entity Recognition (NER)
- 4. Jim did not like the store. It did not have chocolate. He could not find anyone to help him.
- 5. Paris is a lovely city.
- 6. Paris enjoys flying to Asia.
- 7. Paris sails are fun. (Presume this is a bad transcription of audio)
- 8. NER Overview ● Classify individual spans, or sequence of tokens, in a text ● Types Classification ○ Hard Classification ○ Soft Classification ● Types of Methods ○ Machine Learning ○ Rules-Based
- 9. NER Labels ● Locations ○ LOC - Location ○ GPE - Geopolitical Entity ● PERSON ● NORP - Nationalities, religious, or political groups ● TIME ● DATE ● EVENT ● PRODUCT ● FAC - Buildings, airports, highways, bridges, etc.
- 10. Brief Recap on Vectors or Embeddings
- 12. Representing Texts Digitally Bag-of-Words ● The apple is in the tree. ○ 1-the ○ 2-apple ○ 3-is ○ 4-in ○ 1-the ○ 5-tree ● [1, 2, 3, 4, 1, 5]
- 13. Representing Texts Digitally Embeddings ● The apple is in the tree. ○ 1-[0.01234, -0.23456, 0.87654, 0.45678, -0.56123, 0.65432, 0.12345, -0.77123, 0.08456, 0.34567, ...] ○ 2-different vector ○ 3-different vector ○ 4-different vector ○ 1-[0.01234, -0.23456, 0.87654, 0.45678, -0.56123, 0.65432, 0.12345, -0.77123, 0.08456, 0.34567, ...] ○ 5-different vector
- 14. Vector Databases
- 15. Vector Database What is it? ● It holds vectors in a database as storage. ● Similar vectors are stored closer.
- 17. Vector Database How do we use a vector database? ● We populate a vector database with by using a machine learning model to vectorize data and send them to the database.
- 18. Vector Database Why use a vector database?
- 19. Vector Database Why use a vector database? ● Vector databases allow users to store vector data in a way that allows users to query it and find similarity based on a vector-level similarity, rather than explicit human-defined similarity.
- 20. Vector Database What is it? ● A vector database holds numerous vectors or embeddings of data. Sometimes, the database will also store the original data alongside these vectors.
- 23. Vector Database Stacks What is available to us? ● Python, Annoy, Streamlit ○ Cheap, easy to deploy, great for smaller datasets, but requires a little bit of knowledge to build from scratch ○ Best for smaller databases (under 10,000 data) ● Python, txtAI ○ Cheap and easy to use, more resource intensive but easy to deploy ○ Allows for easy interpretability (via highlighting)
- 24. Vector Database Stacks What are available to us? ● Python/JavaScript and Weaviate ○ Open-source ○ Can be done locally, on a server, or via the Weaviate paid-hosting ○ API is easy to use and easy to setup
- 26. Multi-Modal What is it? ● Multi-modal data mining is when we use one type of data to find data of a different type. ● We could use text to find images (which do not have metadata or descriptions) or images to find text.
- 27. Multi-Modal How does it work?
- 29. How tall is Wookie?
- 31. How tall is Wookie?
- 32. RAG What is it? ● RAG allows for you to combine the strengths of large language models (LLMs) with vector databases ● It limits the chances for an LLM to hallucinate (generate fake information) ● It uses a vector database to find relevant material to a query
- 33. RAG What is it? ● RAG allows for you to combine the strengths of large language models (LLMs) with vector databases ● It limits the chances for an LLM to hallucinate (generate fake information) ● It uses a vector database to find relevant material to a query