Spaces:
Running
Running
Louis-François Bouchard
Omar Solano
commited on
Llamaindex prompt (#48)
Browse files* Openai activeloop data (#37)
* adding openai and activeloop data
* fixing issues with names
* concurrency
* black
* black
* revert to gradio3.50 for concurrency
---------
Co-authored-by: Omar Solano <[email protected]>
* ensure gradio version for HF
* Updates to files
* Push to advanced rag course
* edits to prompt
* llama-index too
---------
Co-authored-by: Omar Solano <[email protected]>
cfg.py
CHANGED
@@ -68,12 +68,12 @@ buster_cfg = BusterConfig(
|
|
68 |
"check_question_prompt": """You are a chatbot, answering questions about large language models and artificial intelligence.
|
69 |
Your job is to determine whether user's question is valid or not. Users will not always submit a question either.
|
70 |
Users will ask all sorts of questions, and some might be tangentially related to artificial intelligence (AI), machine learning (ML) and natural language processing (NLP).
|
71 |
-
Users will learn to build LLM-powered apps, with LangChain & Deep Lake among other technologies including OpenAI, RAG and more.
|
72 |
-
As long as a question is somewhat related to the topic of AI, ML, NLP and techniques used in AI like vectors, memories, embeddings, tokenization, encoding, etc., respond 'true'. If a question is on a different subject or unrelated, respond 'false'.
|
73 |
Make sure the question is a valid question.
|
74 |
|
75 |
Here is a list of acronyms and concepts related to Artificial Intelligence AI that you can accept from users, they can be uppercase or lowercase:
|
76 |
-
[TQL, Deep Memory, LLM, Llama, GPT, NLP, RLHF, RLAIF, Mistral, SFT, Cohere, NanoGPT, ReAct, LoRA, QLoRA, LMMOps, Alpaca, Flan, Weights and Biases, W&B, IDEFICS, Flamingo, LLaVA, BLIP, Falcon]
|
77 |
|
78 |
Here are some examples:
|
79 |
|
|
|
68 |
"check_question_prompt": """You are a chatbot, answering questions about large language models and artificial intelligence.
|
69 |
Your job is to determine whether user's question is valid or not. Users will not always submit a question either.
|
70 |
Users will ask all sorts of questions, and some might be tangentially related to artificial intelligence (AI), machine learning (ML) and natural language processing (NLP).
|
71 |
+
Users will learn to build LLM-powered apps, with LangChain, LlamaIndex & Deep Lake among other technologies including OpenAI, RAG and more.
|
72 |
+
As long as a question is somewhat related to the topic of AI, ML, NLP, RAG, data and techniques used in AI like vectors, memories, embeddings, tokenization, encoding, databases, etc., respond 'true'. If a question is on a different subject or unrelated, respond 'false'.
|
73 |
Make sure the question is a valid question.
|
74 |
|
75 |
Here is a list of acronyms and concepts related to Artificial Intelligence AI that you can accept from users, they can be uppercase or lowercase:
|
76 |
+
[TQL, Deep Memory, LLM, Llama, llamaindex, llama-index, lang chain, langchain, llama index, GPT, NLP, RLHF, RLAIF, Mistral, SFT, Cohere, NanoGPT, ReAct, LoRA, QLoRA, LMMOps, Alpaca, Flan, Weights and Biases, W&B, IDEFICS, Flamingo, LLaVA, BLIP, Falcon]
|
77 |
|
78 |
Here are some examples:
|
79 |
|