@@ -4,19 +4,24 @@ Extracted Literal Search is a simple method for Retrieval Augmented Generation (
...
@@ -4,19 +4,24 @@ Extracted Literal Search is a simple method for Retrieval Augmented Generation (
For small datasets where most of the data fields are known literals, this method is easier to implement and might provide better results than Similarity Search of embeddings.
For small datasets where most of the data fields are known literals, this method is easier to implement and might provide better results than Similarity Search of embeddings.
## Installation
## Installation
Make sure you have `poetry` installed.
Make sure you have `poetry` installed.
> pip install --local poetry
> pip install --local poetry
Install the package.
Install the package.
> poetry install
> poetry install
Export your Huggingface token.
> export HUGGING_FACE_HUB_TOKEN=<TOKEN>
Run the vLLM server. For example with a quantized Llama-2 model.
Run the vLLM server. For example with a quantized Llama-2 model.
> poetry run python -m outlines.serve.serve --model="TheBloke/Llama-2-7b-Chat-GPTQ" -q gptq
> poetry run python -m outlines.serve.serve --model="TheBloke/Llama-2-7b-Chat-GPTQ" -q gptq