cleaning files

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+ PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,44 @@
+import os
+from pathlib import Path
+from llama_index.embeddings import HuggingFaceEmbedding, VoyageEmbedding
+from llama_index import (load_index_from_storage, ServiceContext, StorageContext)
+from llama_index import download_loader, SimpleDirectoryReader
+from llama_index.retrievers import RecursiveRetriever
+from llama_index.query_engine import RetrieverQueryEngine
+from llama_index.llms import Anyscale
+from fastapi import FastAPI
+
+app = FastAPI()
+
+# Define the inference model
+llm = Anyscale(model="mistralai/Mistral-7B-Instruct-v0.1", api_key=os.getenv("ANYSCALE_API_KEY"))
+# Define the embedding model used to embed the query.
+# query_embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-base-en-v1.5")
+embed_model = VoyageEmbedding(model_name=model_name, voyage_api_key=os.getenv("VOYAGE_API_KEY"))
+service_context = ServiceContext.from_defaults(llm=llm, embed_model=embed_model)
+
+if "index" in os.list():
+    storage_context = StorageContext.from_defaults(persist_dir=Path("./index"))
+else: 
+    UnstructuredReader = download_loader('UnstructuredReader')\n",
+    dir_reader = SimpleDirectoryReader(Path('./docs/'), file_extractor={".pdf": UnstructuredReader()
+    documents = dir_reader.load_data()
+    index = VectorStoreIndex.from_documents(documents, service_context=service_context, show_progress=True)
+    index.storage_context.persist(Path('index'))
+    storage_context = StorageContext.from_defaults(persist_dir=Path("./index"))
+
+# Load the vector stores that were created earlier.
+index = load_index_from_storage(storage_context=storage_context, service_context=service_context)   
+
+# Define query engine:
+index_engine = index.as_retriever(similarity_top_k=4)
+index_retriever = RecursiveRetriever("vector",retriever_dict={"vector": index_engine})
+query_engine = RetrieverQueryEngine.from_args(index_retriever, service_context=service_context)        
+
+# Deploy the Ray Serve application.
+@app.get("/generate")
+def generate(query: str):
+    return str(query_engine.query(query))
+
+if __name__ == '__main__':
+    uvicorn.run('main:app', reload=True)