TSVGlobal

On a model like GPT, we should be doing normalization on the vectors that correspond to the individual tokens within the blocks/sequence. Because we want to normalize the vectors for...

I feel the question makes a lot of sense. would you expect something like this? ``` # import from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings from langchain.text_splitter import CharacterTextSplitter from langchain.vectorstores import Chroma...

The base chat model does seem to support cache. Am i missing something here?: [https://github.com/hwchase17/langchain/blob/81eebc40702ff676c2f62c42ab4c6732ff794164/langchain/chat_models/base.py](url) ``` class BaseChatModel(BaseLanguageModel, ABC): cache: Optional[bool] = None ##Caching supported in base model verbose: bool...

It is a good practice to explicitly persist ``` # Explicitl persist db.persist() ```

> @JackLeick I did some investigation around this and feel your issue is valid. Following is the summary. Do let me know if it addresses your problem statement. _**Issue**_ the...

Issue has been addressed via commit : https://github.com/hwchase17/langchain/commit/a2830e3056e4e616160b150bf5ea212a97df2dc4

**My understanding** It seems that you want to create a chain to query your database and add memory to the chain to maintain the context of the conversation. You are...

**My understanding** It seems that you want to create a chain to query your database and add memory to the chain to maintain the context of the conversation. You are...

CLA Signed ``` Thank you! Thank you for taking the time to register as an open source contributor. You may print the submission below for your records. You can resubmit...