feat: define corebase

.gitignore

@@ -0,0 +1,9 @@
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+

Dockerfile

@@ -0,0 +1,17 @@
+# Use an official Python runtime as a parent image
+FROM python:3.8-slim-buster
+
+# Set the working directory in the container to /app
+WORKDIR /app
+
+# Add the current directory contents into the container at /app
+ADD . /app
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Make port 80 available to the world outside this container
+EXPOSE 8000
+
+# Run app.py when the container launches
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

apis/configs/llm_configs.py

@@ -0,0 +1,9 @@
+import os
+from langchain_openai import ChatOpenAI
+from langchain_google_genai import ChatGoogleGenerativeAI
+
+
+gpt_model = ChatOpenAI(api_key=os.environ.get('OPENAI_API_KEY'), temperature=0,
+                       request_timeout=120, streaming=True, model="gpt-3.5-turbo-0125")
+gemini_model = ChatGoogleGenerativeAI(api_key=os.environ.get(
+    'GOOGLE_API_KEY'), temperature=0, model="gemini-pro", request_timeout=120)

apis/configs/word_embedding_config.py

@@ -0,0 +1,4 @@
+from langchain_community.embeddings import HuggingFaceEmbeddings
+
+
+mxbai_embedder = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")

main.py

@@ -0,0 +1,19 @@
+import os
+import uvicorn
+from apis import api_v1_router
+from apis.create_app import create_app
+from dotenv import load_dotenv, find_dotenv
+
+# Load environment variables from the `.env` file
+load_dotenv(find_dotenv())
+# Create FastAPI app instance
+app = create_app()
+
+
+# Add routes
+app.include_router(api_v1_router, prefix="/api")
+
+
+# Launch FastAPI app
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=os.environ.get("PORT", 7860))

test.py

@@ -0,0 +1,50 @@
+from langchain_google_genai import ChatGoogleGenerativeAI
+from dotenv import load_dotenv
+import os
+from langchain_community.document_loaders import PyPDFLoader
+from langchain import hub
+from langchain_chroma import Chroma
+from langchain_community.document_loaders import WebBaseLoader
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+from langchain_openai import OpenAIEmbeddings
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+
+
+mxbai_embedder = HuggingFaceEmbeddings(model_name="mixedbread-ai/mxbai-embed-large-v1")
+
+load_dotenv()
+
+llm = ChatGoogleGenerativeAI(google_api_key=os.environ.get("GOOGLE_API_KEY"), 
+                                   model="gemini-1.5-pro-latest")
+
+# Load and split the PDF document into pages
+pdf_loader = PyPDFLoader("LeaveNoContextBehind.pdf")
+pages = pdf_loader.load_and_split()
+
+# Split the pages into smaller chunks
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+splits = text_splitter.split_documents(pages)
+
+# Create a vector store from the document splits
+vectorstore = Chroma.from_documents(documents=splits, embedding=mxbai_embedder)
+
+# Retrieve and generate using the relevant snippets of the blog
+retriever = vectorstore.as_retriever()
+prompt = hub.pull("rlm/rag-prompt")
+
+def format_docs(docs):
+    return "\n\n".join(doc.page_content for doc in docs)
+
+# Define the RAG chain
+rag_chain = (
+    {"context": retriever | format_docs, "question": RunnablePassthrough()}
+    | prompt
+    | llm
+    | StrOutputParser()
+)
+
+# Invoke the RAG chain with a question
+response = rag_chain.invoke("Can you summarize the document?")
+print(response)