Our great sponsors
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
langchain
Discontinued ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain] (by hwchase17)
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
you could use ntlk to summarize the text before you send it GPT-4.
I have a script that uses NLTK to do this. It needs cleaned up but it could be a starting point.
Check out llama_index at https://github.com/jerryjliu/llama_index. What it does: it creates an index over your data using OpenAI embeddings vectors, using the OpenAI Ada model. When querying, it compiles as much context out of this index as fits into GPT, based on similarity to your prompt. Be cautious however: when I experimented with this, GPT-4 support with it‘s larger context size was not there yet. I have landed https://github.com/hwchase17/langchain/pull/1778, but I never wound up submitting another, yet similar patch (to llama_index? Don‘t remember). Make sure that the GPT-4 context is really fully used, and not some smaller size is assumed. Also, ensure that GPT-4 is used as the LLM in the first place: the defaults used to be the older models.
Check out llama_index at https://github.com/jerryjliu/llama_index. What it does: it creates an index over your data using OpenAI embeddings vectors, using the OpenAI Ada model. When querying, it compiles as much context out of this index as fits into GPT, based on similarity to your prompt. Be cautious however: when I experimented with this, GPT-4 support with it‘s larger context size was not there yet. I have landed https://github.com/hwchase17/langchain/pull/1778, but I never wound up submitting another, yet similar patch (to llama_index? Don‘t remember). Make sure that the GPT-4 context is really fully used, and not some smaller size is assumed. Also, ensure that GPT-4 is used as the LLM in the first place: the defaults used to be the older models.
Longer sequence length in transformers is an active area of research (see e.g the great work from the Flash-attention team - https://github.com/HazyResearch/flash-attention), and I'm sure will improve things dramatically very soon.
Related posts
- Creating a Sales Analysis Application with Streamlit: A Practical Approach to Business Intelligence
- Building a Production-Ready Web App with T3 Stack
- Show HN: I built a small utility that handles multiple browser instances for you
- Show HN: Open-source SDK for creating custom code interpreters with any LLM
- PyNQ: Python LINQ for the Masochistic and Deranged