Add doc2cache recipe

.github/workflows/test.yml

@@ -50,4 +50,4 @@ jobs:
         GCP_REGION: ${{ secrets.GCP_REGION }}
         GCP_PROJECT_ID: ${{ secrets.GCP_PROJECT_ID }}
       run: |
-        pytest --verbose --nbval-lax python-recipes/RAG/ python-recipes/vector-search python-recipes/redis-intro --ignore python-recipes/RAG/05_nvidia_ai_rag_redis.ipynb
+        pytest --verbose --nbval-lax python-recipes/RAG/ python-recipes/vector-search python-recipes/redis-intro --ignore python-recipes/RAG/05_nvidia_ai_rag_redis.ipynb python-recipes/semantic-cache/doc2cache_llama3_1.ipynb

README.md

@@ -83,6 +83,7 @@ An estimated 31% of LLM queries are potentially redundant ([source](https://arxi
 
 | Recipe | Description |
 | --- | --- |
+| [/semantic-cache/doc2cache_llama3_1.ipynb](python-recipes/semantic-cache/doc2cache_llama3_1.ipynb) | Build a semantic cache using the Doc2Cache framework and Llama3.1 |
 | [/semantic-cache/semantic_caching_gemini.ipynb](python-recipes/semantic-cache/semantic_caching_gemini.ipynb) | Build a semantic cache with Redis and Google Gemini |
 
 ## Advanced RAG