updating references

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 cache_vector_store_text/** filter=lfs diff=lfs merge=lfs -text
 cache_vector_store_images/** filter=lfs diff=lfs merge=lfs -text
 sentencepiece-0.1.91-cp37-cp37m-manylinux1_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+_data/** filter=lfs diff=lfs merge=lfs -text

README.md

@@ -10,7 +10,30 @@ pinned: false
 short_description: Just another rag but with Images 🖼️
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Just another RAG, dont bother much!!
+
+## File Descriptions
+
+### `z_document_reader.py`
+
+Images are only useful to limited resource computer if it has a caption. So this file helps parse the wikipedia html strips it off the tags.
+
+### `z_embedding.py`
+
+Generates vector store.
+
+### `z_generate.py`
+
+Use LLM and prompting to find the relevant texts and images stored in the vector stores.
+
+## Adding more data sources
+
+Currently limited to wikipedia pages downloaded as HTML.
+
+1. Place the html in the folder `_data`
+2. Run command
+    `python z_embedding.py`
+3. Output will be two FAISS vectors stores in the folder `cache_vector...`
 
 ## Local Debug
 
@@ -29,4 +52,24 @@ Highly recommend VS Code, makes life easy.
 
 1. UI Blocks Concepts: https://huggingface.co/learn/nlp-course/en/chapter9/7
 2. UI Row-Column Arrangement: https://www.gradio.app/guides/controlling-layout
-3. Show caption in image gallery: https://github.com/gradio-app/gradio/issues/3364
+2. Show caption in image gallery: https://github.com/gradio-app/gradio/issues/3364
+2. HF Implementation of basic: https://huggingface.co/learn/cookbook/en/advanced_rag
+2. https://python.langchain.com/docs/integrations/vectorstores/faiss/
+
+
+## Ideas 
+
+1. Shows frames of design patterns: https://www.falkordb.com/blog/advanced-rag/
+2. HF Implementation of basic: https://huggingface.co/learn/cookbook/en/advanced_rag
+2. HF RAG Evaluation: https://huggingface.co/learn/cookbook/en/rag_evaluation
+2. HF Implementation by someone: https://medium.aiplanet.com/advanced-rag-implementation-on-custom-data-using-hybrid-search-embed-caching-and-mistral-ai-ce78fdae4ef6
+2. HF Agentic Rag: https://huggingface.co/learn/cookbook/en/agent_rag
+2. Future read, tooning https://huggingface.co/blog/lucifertrj/finetune-embeddings
+2. Opinion on instruct embeddings: https://huggingface.co/blog/Tonic/instruct-embeddings-and-advanced-rag
+2. Another Implementation: https://huggingface.co/learn/cookbook/en/rag_zephyr_langchain
+2. Another Opinion on ray: https://www.anyscale.com/blog/retrieval-augmented-generation-with-huggingface-transformers-and-ray
+2. Ray Follow up: https://github.com/run-llama/ai-engineer-workshop/blob/main/presentation.pdf?__s=2il5g6hpfc4mtmydioir
+2. llama Index rag implementation: https://docs.llamaindex.ai/en/latest/optimizing/production_rag/
+2. Just some termino book: https://www.projectpro.io/article/advanced-rag-techniques/1063
+2. Another Evaluation Guide: https://pub.towardsai.net/evaluating-rag-metrics-across-different-retrieval-methods-770aa01380c8
+2. Oracle Garbage: https://blogs.oracle.com/ai-and-datascience/post/ai-health-mixtral-oracle-23ai-rag-langchain-streamlit

_data/Cricket World Cup - Wikipedia.htm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef451e07204b8a4775d08482b4062432b7afddc7d05d9775f64279e384398b6
+size 993621