![]() Return answer to user question based on documents uploaded.Send Content Text for matched document chunks along with question text in a prompt to OpenAI completions or chat/completions API (saying something like “answer this questions based on the following context” where you include all of the matched Content Text).Return document chunks with similarity to the question text.Send vectors of question to vector database to search for similar vectors (signifying semantic similarity).Send text of question to OpenAI embedding API to get vectors.Store vectors, original content text, and any needed meta data to a vector database for each chunk.Send each chunk to OpenAI embedding API and get back the vectors.Best if each chunk is a connected idea (so the vectors make the most sense) Parse document into chunks (small enough that you can then send to OpenAI to return word embeddings).I am going to give it a go with Xano to coordinate data flows and do some of the parsing. Main thing is getting a vector database, like Pinecone (or saw Supabase now also supports vectors through pgvector). Ultimately for the use case you are describing I don’t think you’ll need LangChain specifically, though could help with built in functions for what I’ll list out below. Hey! I am going to build out something like this next week. Happy to learn what’s necessary to work with the code, but I don’t know what I need to know to make this all happen. What I need to figure out is how to achieve this as a no-coder. So it seems once I have a handle on how to use Steamship with Replit I should have an API I can call from Bubble. Eventually I’d like to add other functions in Langchain such as memory and chains including other APIs for more specialised results.(Currently I use the Bubble API connector to return results from the OpenAI ChatGPT API with some prompt engineering.) Offer my Bubble users the capability to upload their own documents to be used by ChatGPT or another LLM as necessary.I see ‘fork’ but not ‘clone’ or anything similar. According to Steamship (linked above) I can just clone one of their templates, but coming from no-code and Bubble and not knowing how to code apart from very basic stuff, it’s really not very clear to me what I am supposed to do even just to get started by cloning their template. Replit seems to be the way to go at the moment. GitHub - logspace-ai/langflow: ⛓️ LangFlow is a UI for LangChain, desig. ⛓️ LangFlow is a UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows. Langchain UI GitHub - logspace-ai/langflow: ⛓️ LangFlow is a UI for LangChain, designed with. Here are some useful things I would like to look at making use of, but I’m not entirely sure if or how these things can fit together at the moment: It may be possible for GPT4 to help with coding, however it seems that GPT4 is not aware of Langchain unless the Langchain Docs plugin is used, which I don’t think is available yet. I realise that there is unlikely to be a fully no-code solution at this point. I don’t see any resources on how to get this working at the moment in Bubble, so any pointers or resources that can help to get started on the right path would be a useful resource for anyone else looking for the same things. I’m looking for advice for how to get started adding Langchain and a vector database to my GPT Bubble App to give the app custom knowledge from documents etc.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |