Тёмный

A practical application leveraging Langchain and BigQuery Vector Search 

PracticalGCP
Подписаться 3,2 тыс.
Просмотров 2,3 тыс.
50% 1

Опубликовано:

 

7 сен 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 16   
@user-wf5er3eo8v
@user-wf5er3eo8v Месяц назад
This is a good content. I have a question. I have a uses case where i have a Data which has columns: "customers_reviews","Country","Year","sentiment". I am trying to create a chat bot where it can answer queries like: "Negative comments related to xyz issue from USA from year 2023." for this I need to filter the data for USA and for year 2023 with embeddings for xyz issue to be searched from the database. Which database will be suitable for this: Bigquery or Cloud SQL or Alloy DB. All these have the vector search capabilities. But need to look for most suitable and easy to understand. Thanks
@practicalgcp2780
@practicalgcp2780 Месяц назад
One important thing to understand is the difference between database suitable for highly concurrent traffic (b2c or consumer traffic) vs b2b (internal or external business has small amount of users). BigQuery can be suitable for b2b when the amount of users using it at the same time peak, is low. For all b2c traffic you never want to use BigQuery because it’s not designed for such thing. There are 3 databases on GCP can be suitable for b2c traffic, and all of them supports highly concurrent workload. Cloudsql, alloydb and vertex feature store vector search if you want serverless. You can use any of the 3, whichever you are more comfortable with, vertex feature store can be quite convenient if your data is in BigQuery, a video I create recently might give you some good ideas on how to do this ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-QIZwwCmEhzI.html
@LongHD14
@LongHD14 5 месяцев назад
Wow, this video is incredibly insightful and informative! 👏 I've learned so much and am grateful that you've shared this valuable content with us. Just a quick question: Could I apply these concepts to create a conversation app that details the findings in the search results? Looking forward to your guidance on this.
@practicalgcp2780
@practicalgcp2780 5 месяцев назад
Glad you found it useful! I don’t see why not, but as I mentioned, for a conversational app, I assume you are talking about an app that is consumer (real customers) facing, the concept is exactly the same but you need to change the vector db to something that supports highly concurrent workload. So BigQuery is out of the picture, you can look at vertex AI vector search and also AlloyDB which I am hearing a lot lately. I haven’t tried either yet but as far as I know they are both valid approach for consumer apps supports highly concurrent workload. The docs for alloyDB is here cloud.google.com/alloydb/docs/ai/work-with-embeddings
@LongHD14
@LongHD14 5 месяцев назад
Thank you for your valuable insights and guidance!
@practicalgcp2780
@practicalgcp2780 5 месяцев назад
You are welcome ;)
@LongHD14
@LongHD14 5 месяцев назад
May I ask one more question regarding this matter? I would like to implement permissions for a chat application concerning access to documents. For example, a person should only have access to certain tables or specific fields within those tables, and if they don't have permissions, they wouldn't be able to search. Do you have any suggestions or keywords that might help with this issue? Thank you very much for your assistance
@practicalgcp2780
@practicalgcp2780 4 месяца назад
That is something you have to do through some sort of RBAC implementation (role based access control). That isn’t anything to do with the search, it’s more on mapping out the role of a user through logging in like what most applications do today. Then depends on the role, you can add specific filters in the search queries, like filtering via certain metadata or have a set of tables you can restrict based on roles etc.
@LongHD14
@LongHD14 4 месяца назад
Sure, I understand that. However, I'm looking for a service that can assist me with implementing RBAC.
@practicalgcp2780
@practicalgcp2780 4 месяца назад
ok I see. I think it really depends on what you are using. For example, if you are building a backend with Python. You can use Django which has a RBAC module, but generally any framework would have some sort of RBAC component you can use. If it’s an internal app (like for within the company use) then you can simplify things by just using IAP, but IAP isn’t suitable for external consumer applications
@LongHD14
@LongHD14 4 месяца назад
@@practicalgcp2780 thank you for your answer!
@user-yz6pz3yn6w
@user-yz6pz3yn6w 6 месяцев назад
Hi Richard, tysm for the video, it was really helpfull! Im a jr data scientist working on a customer service chatbot using dialogflow cx and some webhooks for the RAG (product recomendations, stock, price...). My original vector store was VertexAI Vector Search, since its really expensive im looking for other options like BQ Vector Search but you mentioned that a consumer traffic is an issue. Do you have any vector store that you can recomend? Im trying to mantain my solution inside my GCP. Thank you again 🙌
@practicalgcp2780
@practicalgcp2780 6 месяцев назад
Sorry just realised I forgot to reply. I was actually going to look at vertex AI vector search next, as it is one of the good options for vector search, can you provide some metrics on what would you consider as expensive? There are other options like Postgres, elastic search, you can see what you can use from the list langchain has integration with which covers most of them. python.langchain.com/docs/integrations/vectorstores. If you want to control cost better, you can consider the services aren’t based on volume but cost of storage engine. Although you have trade offs on managing infrastructure and also optimising for performance. So it’s more of try and error not a straight answer
@shaboxi129
@shaboxi129 6 месяцев назад
​@@practicalgcp2780 id like to hear more about vertex vector search since i cant find good deep dives on it :(
@user-yz6pz3yn6w
@user-yz6pz3yn6w 6 месяцев назад
​@@practicalgcp2780 The endpoint machine I'm using is quite large (16 vCPUs, 64 GiB). While I'm only working with half the intended volume of products at the moment, the cost is still around $1k per month. I suspect there might be a default parameter set during creation that prevents me from selecting a smaller machine type. I read the integrations and I think my next step is AlloyDB, the good thing about Vertex AI Vector Search is that is really fast so I need to see the difference between those two. Im looking forward to your videos since I haven't seen much content about Vertex AI Vector Search. Thank you for the reply 🙌
@jean9174
@jean9174 5 месяцев назад
😎 "Promosm"
Далее
Centralised Data Sharing using Analytics Hub
31:33
Просмотров 2,8 тыс.
OG Buda - Сабака (A.D.H.D)
02:19
Просмотров 116 тыс.
Я ж идеальный?😂
00:32
Просмотров 81 тыс.
Spring Tips: Vector Databases with Spring AI
23:55
Просмотров 7 тыс.
What's new with BigQuery
46:23
Просмотров 3,3 тыс.
BigQuery to Datastore via Remote Functions
22:20
Просмотров 1,5 тыс.
What is a Vector Database?
8:12
Просмотров 76 тыс.
BigQuery vector search and embedding generation
10:08
RAG in Production - LangChain & FastAPI
11:52
Просмотров 10 тыс.