Build and Deploy a RAG app with Pinecone Serverless

preview_player
Показать описание
We see demand for tools that bridge the gap between prototyping and production. With usage based pricing and support for "unlimited" scaling, Pinecone Serverless helps to address pain points with vectorstore productionization that we've seen from the community. This video builds a RAG chain that connects to a Pinecone Serverless index using LCEL, turns it into an a web service with LangServe, uses Hosted LangServe to deploy it, and uses LangSmith for app observability.

  1. LangChain
Рекомендации по теме
Building a RAG 0:21:14

Building a RAG Based LLM App And Deploying It In 20 Minutes

Build and Deploy 0:24:04

Build and Deploy a RAG app with Pinecone Serverless

Build a RAG 0:24:03

Build a RAG Based LLM App in 20 Minutes! | Full Langflow Tutorial

Build and deploy 0:03:06

Build and deploy a RAG-based chatbot with AI Hub Templates

How to Build 0:45:52

How to Build and Deploy a RAG Model on Your Localhost

How To Deploy 0:55:07

How To Deploy Your RAG/AI App On AWS (Step by Step)

Managed RAG Deployment 0:05:10

Managed RAG Deployment on Amazon Bedrock - Deployed in Minutes

Building a RAG 0:53:15

Building a RAG application using open-source models (Asking questions from a PDF using Llama2)

Building a RAG 0:14:26

Building a RAG System With Gemma, Hugging Face & Elasticsearch

Build your own 0:16:41

Build your own RAG (retrieval augmented generation) AI Chatbot using Python | Simple walkthrough

Build a RAG 0:16:12

Build a RAG app in minutes using Langflow OpenAI and Azure | StudioFP101

How to build 0:34:22

How to build Multimodal Retrieval-Augmented Generation (RAG) with Gemini

Building a RAG 1:12:39

Building a RAG application from scratch using Python, LangChain, and the OpenAI API

Building and deploying 0:08:36

Building and deploying multi-agent RAG systems in 2024 with LlamaIndex

Building Production-Ready RAG 0:18:35

Building Production-Ready RAG Applications: Jerry Liu

Build and Deploy 0:02:12

Build and Deploy a Machine Learning App in 2 Minutes

NVIDIA NIM: The 0:27:19

NVIDIA NIM: The Game-Changer in Gen AI Deployment (Build a RAG)

RAG + Langchain 0:16:42

RAG + Langchain Python Project: Easy AI/Chat For Your Docs

ADVANCED Python AI 0:40:59

ADVANCED Python AI Agent Tutorial - Using RAG

Local Retrieval Augmented 5:40:59

Local Retrieval Augmented Generation (RAG) from Scratch (step by step tutorial)

Build an AI 0:33:34

Build an AI RAG Application with LangChain & Next.js

Build an End-to-End 0:42:59

Build an End-to-End RAG API with AWS Bedrock & Azure OpenAI

Python RAG Tutorial 0:21:33

Python RAG Tutorial (with Local LLMs): AI For Your PDFs

Embedchain: BEST Way 0:13:37

Embedchain: BEST Way to Create Powerful LLM Apps Using RAG! (Opensource)

Комментарии
Автор

Love it!! I've been wondering how to get to this point on deploying a chain on the web to be used, thanks for the video, super useful!!

estevegraells
Автор

Langchain's videos are very good if you are able to hear them. Pun intended. Please improve the voice.

palashjyotiborah
Автор

This is pretty cool, especially the fast API to generate the end points. I was wondering the same question below, how come the context token method was overloaded, Love to get access to this, and give it a go. I've been looking at scalable deployment approaches.

prestonmccauley
Автор

Great content, thank you. Just please next time use bigger fonts

nsyll
Автор

Great video. Thank you for posting it. Quick question: After you expanded the passed information to the complete wiki pages why does the LMM not have an issue with the context length? Does langchain abstract away the limitation of the number of tokens I can pass?

glaunertim
Автор

Congrats 👏 .... Please how can I get access to langSmith? Tks

thiagolaurito
Автор

Great video, but can you built something like that but with ollama to run it locally ?

renierdelacruz
Автор

Looks nice but it's missing the ability to set the temperature and change the model from the webpage UI.

antdx
Автор

Hi, great video!
Do you know if it's possible to automatically create a pinecone db index from code?
So that you don't have to create them manually

quengelbeard
Автор

I am curious to know what you used for the "environment=_ENVIRONMENT" for your Client since

levesseur
Автор

This may be a stupid question, but how do I start from scratch, i.e. srape the wikipedia page, create embeding, create an index, upload the embeddings, ...
I am missing all this stuff in the explanation ...

eugenmalatov
Автор

It would be just great to implement this without the need to use the OpenAI service api, can you explain how to implement the OpenAI alternatives to achieve the same results?

nelohenriq
Автор

I've been trying to get access to langserve but to no avail. Any way I can get access pleaseee?

seansullivan
Автор

Thanks for the video Lance, how can I get access to langsmith?

Orcrambo
Автор

hi martin, how do I contact you for langsmith access?

manfyegoh