Skip to content

Commit

Permalink
Update basic-rag readme & sphinx documentations
Browse files Browse the repository at this point in the history
  • Loading branch information
elpham6 committed Apr 17, 2024
1 parent af20602 commit 027f1c9
Show file tree
Hide file tree
Showing 3 changed files with 16 additions and 9 deletions.
2 changes: 1 addition & 1 deletion cookbook/Basic-RAG/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
Welcome to the Basic RAG Cookbook! This repository is dedicated to showcasing how to utilize the Retrieval-Augmented
Generation (RAG) model for various applications using custom and few-shot prompts. For in depth understanding of RAG
pipelines, chains, and prompts
check [RAG-Piplines.md](https://github.com/arjbingly/Capstone_5/blob/main/projects/Basic-RAG/RAG-Piplines.md)
check [RAG-Pipelines.md](https://github.com/arjbingly/Capstone_5/blob/main/cookbook/Basic-RAG/RAG-PIPELINES.md)

### Contents:

Expand Down
4 changes: 2 additions & 2 deletions src/docs/get_started.installation.rst
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
Installation
===============
*Since we are just in the development phase we have not published to pypi yet.*
*Since we are under the development phase, we have not published to pypi yet.*

* ``git clone`` the repository
* ``pip install .`` from the repository
* *For Developers*: ``pip install -e .``

Moreover, further customization can be made on the config file, `src/config.ini`.
Further customization can be made on the config file, `src/config.ini`.
19 changes: 13 additions & 6 deletions src/docs/get_started.vectordb.rst
Original file line number Diff line number Diff line change
@@ -1,36 +1,42 @@
Vector Stores
===============

# Explain what a vector store is...
Vector store or vector database is a type of database that stores data in high-dimensional vectors.
This is a crucial component of RAG, storing embeddings for both retrieval and generation processes.

Supported Vector Stores
########################

Currently supported vectorstores are:

1. Chroma
2. Deeplake
2. DeepLake

Chroma
*******
Since Chroma is a server-client based vector database, make sure to run the server.

* To run Chroma locally, either use move to `src/scripts` then run `source run_chroma.sh` or refer to
`Running Chroma in ClientServer <https://docs.trychroma.com/usage-guide#running-chroma-in-clientserver-mode>`_.
* To run Chroma locally, either:
1. Move to `src/scripts` then run ``source run_chroma.sh`` OR
2. Refer to `Running Chroma in ClientServer <https://docs.trychroma.com/usage-guide#running-chroma-in-clientserver-mode>`_.
This by default runs on port 8000.
* If Chroma is not run locally, change `host` and `port` under `chroma` in `src/config.ini`, or provide the arguments
* If Chroma is not run locally, change ``host`` and ``port`` under ``chroma`` in `src/config.ini`, or provide the arguments
explicitly.

For non-supported vectorstores, (...)

Embeddings
###########

* By default, the embedding model is `instructor-xl`. Can be changed by changing `embedding_type` and `embedding_model`
* By default, the embedding model is `instructor-xl`. Can be changed by changing ``embedding_type`` and ``embedding_model``
in `src/config.ini` or providing the arguments explicitly.
* Any huggingface embeddings can be used.

Data Ingestion
###############

For more details on data ingestion, refer to our `cookbook<https://github.com/arjbingly/Capstone_5/blob/main/cookbook/Basic-RAG/README.md>`_.

::

client = DeepLakeClient() # Any vectordb client
Expand All @@ -41,3 +47,4 @@ Data Ingestion


retriever.ingest(dir_path)

0 comments on commit 027f1c9

Please sign in to comment.