Simun Sunjic

Does anyone have a working example? I am struggling with the exception that ctx is not properly initialized when I try `docsearch = Chroma.from_documents(documents = texts, embedding = embeddings)` I...

Thanks @traverse-in-reverse I was trying at the end to create a custom wrapper, and also tried Vicuna model, here are some trials if of any value: [vicuna colab](https://colab.research.google.com/drive/12bvA3l-mg7I80V_toA14XK4g0B-8zFxY?usp=sharing)

@traverse-in-reverse found the issue of why I couldn't run my examples, my model couldn't be initialized. I switched to GGML [gpt4all-repo](https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/) and now it works. Not sure why

@AndriyMulyar so this support is not yet developed, right? Any clue about dates? I found nothing in the gpt4all readme

@marc-dsalab you can use some other models, for example: ```python embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2") db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS) llm = GPT4All(model="models/ggml-gpt4all-j-v1.3-groovy.bin", n_ctx=model_n_ctx, backend='gptj', callbacks=callbacks, verbose=False) qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever,...

@TomasMiloCA `HuggingFaceEmbeddings` are from the langchain library, `retriever` is from ChromaDB. Pasting you the real method from my program: ```python def process_database_question(database_name, llm): embeddings = OpenAIEmbeddings() if openai_use else HuggingFaceEmbeddings(model_name=ingest_embeddings_model)...

same

> So what is the solution, in the end, only the use of https links works?

> @sime2408 Please check this solution [#94 (comment)](https://github.com/cyntler/react-doc-viewer/issues/94#issuecomment-1466163408). I have implemented something similar, and it's working fine. You can use the create object method and supply it to URI if...

Pinecone is a vector database, PostgreSQL is not specifically designed for handling high-dimensional vector data, but I assume you should be able to store vector embeddings as arrays or binary...