Indentation error

Where is this bracket that HF is finding?

Added please to the placeholder text.

Syntax error, bracket on line 343

Updated how the gradio looks, and doubled down on the system prompt to ensure that the system refers to the documents as its knowledge base.

Updated the system prompt a bit.

Forgot that I called the function reranker_v1.

Added the reranker to improve the quality of the nodes passed on to the query engine.

It was the docstring with the indentation error lol.

Indentation error.

Indent error fix

Forgot to update the package imports to bring in the extractor for the log handler

Changed the temperature to 0.5, and added a function that will extract the condensed question for analysis.

Change the temp to 1

Changed temperature

Update app.py

Added a prompt helper to help manage the tokens, reduced the summary size to 800

Memory issues solved

Added a background wait to counter the problem

Specified chat mode, and made sure that the message was streamed for a nice UI action.

Added a memory buffer, and moved the wait llm function to the main bit for gradio.

Checking something

I have added some server specifics because the gradio bit isn't starting up.

Changed the model from FP4 to AWQ

Moved the embedding model to the CPU. This will allow me to have more space on the GPU for the LLM.

Switched the model from Llama 3.3-70B to Llama-3.3-70B-Instruct-FP4.

Added start server and wait for server

Reduced the max-token-sizes to 2048.

Changes added to move to vLLM

Specified the provider (groq) anf edited max new tokens to 16k.

Increased the max new tokens and edited the system prompt to remove the in text citations. Reduced the temperature to 0.5 since there was a lot more faff in the response.

Forgot ot update to the new database.

Removed the sources display to update the look of the chatbot to something more friendly.

Updated the temperature to 0.8 , and the max new tokens to 8192. Removed the context window, might put it in later as 16000.

Updated max new tokens to 4096 to improve the cut offs.

Switched back to an inference provider for speed

I forgot a comma.

Added back in the tokenizer

Removed max_new_tokens

Added the HF_TOKEN collection

Updated HuggingFaceLLM parameters

Removed the provider=auto to fix type error

Changed from the Inference Provider to running the LLM in the space

Update app.py

Changed the temperature to 0 - this is a factual thing we have here uwu.

Changed the prompt a bit.

Forgot a bracket.

Update app.py

Changed the chroma db access

Updated the climate database