41–50 of 100 posts
I was using pinecone before installing pgvector in Postgres. Pinecone works and all but having the vectors in Postgres resulted in an explosion of use for us. Full relational queries with where clauses and order by etc AND vector embeddings is wicked.
there's at least $168m being poured into vector db's this year. recent vector database fundraises: - Chroma - $18M seed https://www.trychroma.com/blog/seed - Weaviate - $50m A https://www.theinformation.com/articles/index-ventures-leads... - Pinecone - $100M B
Imo the most advanced vector DB out there is Vespa https://vespa.ai/ . Harder to set up than wrappers like Chroma, but very powerful.
Isn't there still a token limit as to how much ChatGPT can hold in working memory?
Is the goal that ChatGPT can query the vector database directly to get information out, and if so, how is that different than using a regular database?
Can someone explain how vector databases can be used as long term memory for AI (and LLMs specifically)? Isn't there still a token limit as to how much ChatGPT can hold in working memory? Is the goal that ChatGPT can query the vector database directly to get information out, and if so, how is that different than using a regular database?
So the sentence "I started working as a programmer" will be very close to "I began my job as a software developer". This makes it very powerful for natural language search.
So when the user asks a bot "Find the text message John sent me 3 years ago about wanting to found a company, I think it was like a hang gliding company? or parasailing? idk"
Behind the scenes you can ask GPT "Output a list of 10 candidate sentences that are plausible text messages that John may have sent", and it spits out
"I'm thinking of starting a hang gliding company" and "I might found a parasailing company" etc.
Then you query the vector DB for those imaginary sentences, and as a result you get sentences that are semantically similar. You take the top N nearest neighbors and plug them in to the GPT context window and say:
"Here are 100 sentences that might match the original query. If any of them match, select the number that matches. Otherwise output null"
If you engineer this system well, you can get pretty decent results.
This is great for key:value type querying, but IMO there is a lot of ground to be explored by extending it with more graph-like links. I.e. use vector search to get some initial nodes that are better than random, but then start doing a little beam-search algorithm from those nodes to find nodes they are "linked" to in some way that may answer the query better.
Earlier quoted context omitted.
Respectfully if you don’t know what a vector is, you probably don’t need a vector DB. When they say “vector-search” they mean semantic search. I.e. “which document is the most semantically similar to the query text”. So how do we establish semantic similarity? In a database like Elasticsearch, you store text and the DB indexes the text so you can search. In a vector DB you don’t just store the raw text, you store a v…
Respectfully if you don’t know what a vector is, you probably don’t need a vector DB. I wasn't looking for one ;-) I was looking for a recommendation engine, similarly most often I'm looking for various ways to use ML and AI to improve various features and workflows. Which I guess is my point, I don't know who Pinecone's target market is but from following this thread it seems like all the folks who know how to do wh…
emb = model(text)
emb1 = model(text1)
emb2 = model(text2)
similarity = sum([a * b for a, b in zip(emb1, emb2)])
The great thing about embedding text is the simplicity of the API and the similarity operation. It's dead simple to use. You can do clustering, classification, near neighbour search / ranking, recommendation, or any kind of semantic operations between two texts that can be described as a score. If you cache your vectors you can search very very quickly with np.dot or other methods, in a few ms. Today you can also embed images to the same vector space and do image classification by taking the text label with max dot product.
You can also train a very small model on top of embeddings to classify the input into your desired classes, if you can collect a dataset. Embeddings are the best features for text classification. You can think of this embedding method as a way to slice and dice in the semantic space like you do with strings in character space. All fast and local, without GPUs.
there's at least $168m being poured into vector db's this year. recent vector database fundraises: - Chroma - $18M seed https://www.trychroma.com/blog/seed - Weaviate - $50m A https://www.theinformation.com/articles/index-ventures-leads... - Pinecone - $100M B
https://towardsdatascience.com/milvus-pinecone-vespa-weaviat...