From ed5d10aa9fb645ea35156a44970f18dd6f5f8816 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Kacper=20=C5=81ukawski?= Date: Fri, 27 Jan 2023 18:18:32 +0100 Subject: [PATCH] Grammar fixes --- .../content/articles/langchain-integration.md | 36 +++++++++---------- 1 file changed, 17 insertions(+), 19 deletions(-) diff --git a/qdrant-landing/content/articles/langchain-integration.md b/qdrant-landing/content/articles/langchain-integration.md index 3bcd70907..cd2c87470 100644 --- a/qdrant-landing/content/articles/langchain-integration.md +++ b/qdrant-landing/content/articles/langchain-integration.md @@ -22,28 +22,27 @@ keywords: Building applications with Large Language Models don't have to be complicated. A lot has been going on recently to simplify the development, so you can utilize already pre-trained models and support even complex pipelines with a few lines of code. [LangChain](https://langchain.readthedocs.io) -is one of the libraries which provide unified interfaces to different libraries, so you can avoid writing the boilerplate code and focus -on the value you want to bring. +provides unified interfaces to different libraries, so you can avoid writing boilerplate code and focus on the value you want to bring. ## Question Answering with Qdrant in the loop It has been reported millions of times recently, but let's say that again. ChatGPT-like models struggle with generating factual statements if no context is provided. They have some general knowledge but cannot guarantee to produce a valid answer consistently. Thus, it is better to provide some facts we know are actual, so it can just choose the valid parts and extract them from all the provided contextual data to give a comprehensive answer. Vector database, -such as Qdrant, is of great help here, as their ability to perform a semantic search over huge knowledge base is crucial to preselect some possibly valid +such as Qdrant, is of great help here, as their ability to perform a semantic search over a huge knowledge base is crucial to preselect some possibly valid documents, so they can be provided into the LLM. That's also one of the **chains** implemented in LangChain, which is called `VectorDBQA`. And Qdrant got integrated with the library, so it might be used to build it effortlessly. ### What do we need? Surprisingly enough, there will be two models required to set things up. First of all, we need an embedding model that will convert the set of facts into -vectors, and store those into Qdrant. That's an identical process like in any other semantic search application. We're going to use one of the +vectors, and store those into Qdrant. That's an identical process to any other semantic search application. We're going to use one of the `SentenceTransformers` models, so it can be hosted locally. The embeddings created by that model will be put into Qdrant and used to retrieve the most -similar documents, given query. +similar documents, given the query. However, when we receive a query, there are two steps involved. First of all, we ask Qdrant to provide the most relevant documents and simply combine all of them into a single text. Then, we build a prompt to the LLM (in our case OpenAI), including those documents as a context, of course together with the -question asked. So the input to the LLM looks like following: +question asked. So the input to the LLM looks like the following: ```text Use the following pieces of context... @@ -54,18 +53,18 @@ Question: How much is 2 + 2? Helpful Answer: ``` -There might be several context documents combined, and its solely up to LLM to choose the right piece of content. But our expectation is, the model should +There might be several context documents combined, and it is solely up to LLM to choose the right piece of content. But our expectation is, the model should respond with just `4`. -Why do we need two different models? They solve some different tasks. The first model performs feature extraction, by converting the text into vectors, while +Why do we need two different models? Both solve some different tasks. The first model performs feature extraction, by converting the text into vectors, while the second one helps in text generation or summarization. Disclaimer: This is not the only way to solve that task with LangChain. Such a chain is called `stuff` in the library nomenclature. ![](/articles_data/langchain-integration/flow-diagram.png) -Enough theory! This sounds like a pretty complex applications, as it involves several systems. But with LangChain, it might be implemented in just a few lines +Enough theory! This sounds like a pretty complex application, as it involves several systems. But with LangChain, it might be implemented in just a few lines of code, thanks to the recent integration with Qdrant. We're not even going to work directly with `QdrantClient`, as everything is already done in the background -by LangChain. If you want to get into the source code right away, all the processing available as a +by LangChain. If you want to get into the source code right away, all the processing is available as a [Google Colab notebook](https://colab.research.google.com/drive/19RxxkZdnq_YqBH5kBV10Rt0Rax-kminD?usp=sharing). ## Implementing Question Answering with LangChain and Qdrant @@ -79,10 +78,10 @@ so we need an API key. The same is for OpenAI - the API key has to be obtained f ### Building the knowledge base -We also need some facts from which the answers will be generated from. There is plenty of public datasets available, and -[Natural Questions](https://ai.google.com/research/NaturalQuestions/visualization) is one of them. It consists of whole HTML content of the websites they were -scraped from. That means we need some preprocessing to extract plain text content. As a result we're going to have two lists of strings - one for questions -and the other ones for the answers. +We also need some facts from which the answers will be generated. There is plenty of public datasets available, and +[Natural Questions](https://ai.google.com/research/NaturalQuestions/visualization) is one of them. It consists of the whole HTML content of the websites they were +scraped from. That means we need some preprocessing to extract plain text content. As a result, we’re going to have two lists of strings - one for questions and +the other one for the answers. The answers have to be vectorized with the first of our models. The `sentence-transformers/all-mpnet-base-v2` is one of the possibilities, but there are some other options available. LangChain will handle that part of the process in a single function call. @@ -91,15 +90,14 @@ other options available. LangChain will handle that part of the process in a sin ### Setting up QA with Qdrant in a loop -`VectorDBQA` is a chain that performs the process described above. So it, first of all, loads some facts from Qdrant and then feed them into OpenAI LLM -that should analyze them to find the answer to given question. The only last thing to do before using it is putting things together, also with a single -function call. +`VectorDBQA` is a chain that performs the process described above. So it, first of all, loads some facts from Qdrant and then feeds them into OpenAI LLM which +should analyze them to find the answer to a given question. The only last thing to do before using it is to put things together, also with a single function call. ![](/articles_data/langchain-integration/code-vectordbqa.png) ## Testing out the chain -And that's it! We can put some queries, and LangChain will perform all the required processing to find the answer in a provided context. +And that's it! We can put some queries, and LangChain will perform all the required processing to find the answer in the provided context. ![](/articles_data/langchain-integration/code-answering.png) @@ -121,7 +119,7 @@ And that's it! We can put some queries, and LangChain will perform all the requi ``` The great thing about such a setup is that the knowledge base might be easily extended with some new facts and those will be included in the prompts -sent to LLM later on. Of course, assuming their similarity to given question will be in top results returned by Qdrant. +sent to LLM later on. Of course, assuming their similarity to the given question will be in the top results returned by Qdrant. If you want to run the chain on your own, the simplest way to reproduce it is to open the [Google Colab notebook](https://colab.research.google.com/drive/19RxxkZdnq_YqBH5kBV10Rt0Rax-kminD?usp=sharing).