How does this handle websites with complicated structure instead of your typical blogposts where ideas are divided neatly into separate paragraph?
Your website's content -> Q&A bot / chatbot
11–20 of 28 posts
Re: Your website's content -> Q&A bot / chatbot
#12I tried to do something tangentially similar recently, telling ChatGPT that I'd ask it a question, but rather than a response, I wanted search terms for Wikipedia and Wikidata that I could give it that would have the answer in. The thinking is I'd then be able to provide those to it, and get it to synthesize that data, providing answers that had decent citations in them.
Perhaps it was the example I chose "flight time from New York to London" but I couldn't really get it to provide sensible search terms for the information it wanted or needed
Re: Your website's content -> Q&A bot / chatbot
#13I tried to do something tangentially similar recently, telling ChatGPT that I'd ask it a question, but rather than a response, I wanted search terms for Wikipedia and Wikidata that I could give it that would have the answer in. The thinking is I'd then be able to provide those to it, and get it to synthesize that data, providing answers that had decent citations in them. Perhaps it was the example I chose "flight tim…
Check out langchain. It implements the ReAct approach, which is similar to what you describe, but without a human needing to be the go-between.
Re: Your website's content -> Q&A bot / chatbot
#14Reading the readme makes me think it's only searching the top 4 most likely docs via the embeddings, not the wiki at any time? or am I misunderstanding how this works? With embeddings being close to just term vector matching via dot(?) product? So basically get all the sub-prhases/sounds -> vector -> check vector db for closest matching documents -> send to gpt for summarization and answering the quetsion. If that's…
Yep, that's the way it's currently implemented in langchain.
The 4 is a hyperparameter you can change, though, so you could set it to 10 as well.
The way it works is that it first looks up the N most relevant documents (N being 4 in the default case) in the FAISS store relevant to the question, so it uses distance of embedding vectors for this lookup.
Then it uses GPT3 to get summaries of the 4 entries related to the question and finally all the summaries together with the question will lead to the answer.
In doing so, you can trace the source where the answer came from and can also point to that URL in the end.
When you make N larger it just gets more expensive in terms of your API costs.
Re: Your website's content -> Q&A bot / chatbot
#15Nice to have tools like this to wrap up features, definitely makes these types of solutions more accessible, thanks! It would be nice to know from your experience if there is a kind of rule of thumb for calculating cost of fine tuning and running a solution like this against a docs site?
I don't have larger scale experience on this at the moment, but I can tell you what I observed during my trials (also see my related blog entry for some more info: https://www.paepper.com/blog/posts/build-q-and-a-bot-of-your...)
It cost around 0.05$ to create the embeddings for my ~50 blog entries.
Asking a question in the way I've described it also costs around 0.05$ via the API.
Re: Your website's content -> Q&A bot / chatbot
#16I would absolutely love to take our internal Wiki and use this against it.
Go for it, it's quite easy to do, you only need to adapt the `https://github.com/mpaepper/content-chatbot/blob/main/create...` file a bit to match the way your data is represented and then you are good to go.
Re: Your website's content -> Q&A bot / chatbot
#17How does this handle websites with complicated structure instead of your typical blogposts where ideas are divided neatly into separate paragraph?
Currently, it only splits documents linearly, so if you have information which is written backwards or things like that, it will likely not work so well.
Re: Your website's content -> Q&A bot / chatbot
#18Awesome! Are you planning on adding agent/tools support? It would be cool to use this with internal data, then allow clients to chat with a bot fine-tunes on their data, but that can also run queries, or get reports for specific dates, or charts, all via tools.
Yes, this will be an interesting next experiment - adding agents with additional tools (also for example access to internal APIs) will be quite powerful.
Re: Your website's content -> Q&A bot / chatbot
#19Reading the readme makes me think it's only searching the top 4 most likely docs via the embeddings, not the wiki at any time? or am I misunderstanding how this works? With embeddings being close to just term vector matching via dot(?) product? So basically get all the sub-prhases/sounds -> vector -> check vector db for closest matching documents -> send to gpt for summarization and answering the quetsion. If that's…
Yep, that's the way it's currently implemented in langchain. The 4 is a hyperparameter you can change, though, so you could set it to 10 as well. The way it works is that it first looks up the N most relevant documents (N being 4 in the default case) in the FAISS store relevant to the question, so it uses distance of embedding vectors for this lookup. Then it uses GPT3 to get summaries of the 4 entries related to the…
Looks interesting! Have you considered a proper vector database like Qdrant (https://qdrant.tech)? FAISS runs on a single machine, but if you want to scale things up, then a real database makes it a lot easier. And with a free 1GB cluster on Qdrant Cloud (https://cloud.qdrant.io), you can store quite a lot of vectors. Qdrant is also already integrated with Langchain.
Re: Your website's content -> Q&A bot / chatbot
#20Earlier quoted context omitted.
Yep, that's the way it's currently implemented in langchain. The 4 is a hyperparameter you can change, though, so you could set it to 10 as well. The way it works is that it first looks up the N most relevant documents (N being 4 in the default case) in the FAISS store relevant to the question, so it uses distance of embedding vectors for this lookup. Then it uses GPT3 to get summaries of the 4 entries related to the…
Looks interesting! Have you considered a proper vector database like Qdrant ( https://qdrant.tech )? FAISS runs on a single machine, but if you want to scale things up, then a real database makes it a lot easier. And with a free 1GB cluster on Qdrant Cloud ( https://cloud.qdrant.io ), you can store quite a lot of vectors. Qdrant is also already integrated with Langchain.
Probably not very helpful at the scale most people would run this. Even brute forcing the search on CPU gives results in a few ms on small datasets.