tree-of-thought-prompting
llama-retrieval-plugin
tree-of-thought-prompting | llama-retrieval-plugin | |
---|---|---|
8 | 14 | |
589 | 322 | |
- | 0.0% | |
5.3 | 4.3 | |
6 months ago | about 1 year ago | |
Python | ||
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tree-of-thought-prompting
- Ask HN: Any good collection of writing prompts for GPT 3.5/4?
-
GitHub - Secrets of Tree of Thoughts for Programmers 🌳👨💻
Tree of Thoughts Prompting or framework is techniques to get the model to diversify its output and self-evaluate its response.
-
Questions about memory, tree-of-thought, planning
2 - Probably too early in testing and development for there to be a 'standard'. A quick google search will find you some stuff to read like https://github.com/dave1010/tree-of-thought-prompting, but your best bet is to read through the stuff other people are doing and try things for yourself. You might end up discovering something new that nobody has thought of yet. Kaio Ken literally just changed the game overnight and figured out how to expand context to 8k for llama-based models with 2 lines of code. Things are evolving fast and the community desperately needs people willing to spend time reading papers on Arxiv, digging through githubs, and testing stuff out.
- What size model is needed for Reasoning?
-
Puzzle GPT: Highly Effective and Fun Puzzle-Solving Prompt for GPT-4 (Uses CoT & ToT)
Source: Conversation with Bing, 6/4/2023 (1) Chain-of-Thought Prompting | Prompt Engineering Guide. https://www.promptingguide.ai/techniques/cot. (2) [2305.10601] Tree of Thoughts: Deliberate Problem Solving with Large .... https://arxiv.org/abs/2305.10601. (3) [2201.11903] Chain-of-Thought Prompting Elicits Reasoning in Large .... https://arxiv.org/abs/2201.11903. (4) Using Tree-of-Thought Prompting to boost ChatGPT's reasoning. https://github.com/dave1010/tree-of-thought-prompting. (5) Tree of Thoughts: Deliberate Problem Solving with Large Language Models. https://arxiv.org/pdf/2305.10601.pdf. ```
- Tekoäly on jo osittain ohittanut ihmisen. Kehitysvauhdin kiihtyessä tärkeä kysymys on, kenen etiikkaa AI noudattaa. Ykkösaamun vieraana on professori Teemu Roos Suomen tekoälykeskuksesta. Seija Vaaherkumpu haastattelee.
-
How close are we to an AutoGPT (or similar programme) that can improve its own code recursively?
That’s not exactly correct. Tree of thought prompting can boost reasoning. Check out the GitHub. https://github.com/dave1010/tree-of-thought-prompting
- Using Tree of Thought Prompting to boost ChatGPT's reasoning
llama-retrieval-plugin
-
Readability Score Analysis
For the demonstration purpose, you will be guided with the prompt execution using the Lastmile AI. However, you are free to execute the prompt directly on ChatGPT or other LLMs. If you are a developer, you may programmatically execute the prompt or provide an API or a service to your customers.
-
AI Artist of your choice with AiConfig
For the demonstration purposes, we'll be making use of AiConig driven approach of LastMileAI. If you are new to the LastMileAI or AiConfig, I request you to please read the following blogs
-
Systematic Modern Artwork with AiConfig
Hope you had a lot of fun with the AiConfig, systematic instruction driven modern artwork using the AiConfig and LastMileAI workbook. That said, your creativity or imagination is the only limit.
-
Prompt Routing with Zeroshot Technique -AiConfig
Hope you had a lot of fun with the AiConfig, Prompt routing and using the LastMileAI workbook. Creativity or imagination is the limit. You can potentially create or build any useful AI based apps or service in a matter of minutes.
-
Trend Detection and Analysis with the AiConfig
You need to do the following steps and tweak the prompts based on your requirements. Especially the context or the content for which you wish to perform the trend analysis. There are two ways with which you could execute the AiConfig. Here is the first option of using the config and load it up to LastMileAI and perform the cell by cell execution from top to bottom.
-
State of the Art Prompt Builder with AiConfig
When it comes to the hands on, As a preference, AiConfig is the framework through which you will be presented with the prompt building mechanism. There are various reasons like easy to iterate, test and see the responses in real-time with the LastMileAI Workbook. When it comes to the Prompt Chaining I personally prefer the AiConfig and the Workbook approach. However, it's purely optional for this development.
-
Master Prompt Engineering with OpenAI 🧠
Our team at LastMile AI built a Streamlit app powered by AIConfig that lets you experiment with OpenAI's strategies on your prompts.
-
Human and AiConfig - Life is all about Composition
Now that you have understood the meaning and importance of "Composition", you will be guided with the mechanism to have a hands-on experience. For this purpose, we'll be making use of AiConig driven approach of LastMileAI. If you are new to the LastMileAI or AiConfig, I request you to please read the following blogs
-
Prompt Chaining with AiConfig
I would highly recommend you to start using the LastMileAI workbooks for building the prompt based apps. Download the AiConfig and then start playing with it. Finetune as per your requirements and design or develop an API to serve the prompt based AI Apps.
-
Questions about memory, tree-of-thought, planning
Mhh, a viable alternative might be to setup a locally hosted search engine, like SearX and then use a LLM in conjunction with the llama-retrieval-plugin, that also gives you a database that is human readable and the LLM can give direct links to the source.
What are some alternatives?
tree-of-thought-llm - [NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
chatgpt-retrieval-plugin - The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
gpt_jailbreak_status - This is a repository that aims to provide updates on the status of jailbreaking the OpenAI GPT language model.
aiconfig - AIConfig is a config-based framework to build generative AI applications.
manticoresearch - Easy to use open source fast database for search | Good alternative to Elasticsearch now | Drop-in replacement for E in the ELK soon
LocalAI - :robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.
Weaviate - Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
streamlit_apps - collection of streamlit apps
ChatRWKV - ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
txtinstruct - 📚 Datasets and models for instruction-tuning
guidance - A guidance language for controlling large language models. [Moved to: https://github.com/guidance-ai/guidance]