Using docker image

Dockerfile

@@ -1,8 +1,9 @@
 FROM python:3.11
 FROM docker
 
-RUN docker pull qdrant/qdrant
-RUN docker run -p 6333:6333 qdrant/qdrant
+RUN systemctl start docker
+RUN docker pull kushagrash13/patent-image:1.0
+RUN docker run -p 6333:6333 kushagrash13/patent-image:1.0
 
 # Set working directory
 WORKDIR /code
@@ -23,4 +24,4 @@ ENV HOME=/home/user \
 WORKDIR $HOME/app
 
 # Start Qdrant and the application
-CMD ["python3 ingest.py", "uvicorn app:app --host 0.0.0.0 --port 7860"]
+CMD ["uvicorn app:app --host 0.0.0.0 --port 7860"]

app.py

@@ -1,16 +1,16 @@
+import os
+import json
+from langchain_groq import ChatGroq
 from langchain import PromptTemplate
+from qdrant_client import QdrantClient
 from langchain.chains import RetrievalQA
-from langchain.embeddings import SentenceTransformerEmbeddings
-from fastapi import FastAPI, Request, Form, Response
+from langchain.vectorstores import Qdrant
 from fastapi.responses import HTMLResponse
-from fastapi.templating import Jinja2Templates
 from fastapi.staticfiles import StaticFiles
 from fastapi.encoders import jsonable_encoder
-from qdrant_client import QdrantClient
-from langchain.vectorstores import Qdrant
-import os
-import json
-from langchain_groq import ChatGroq
+from fastapi.templating import Jinja2Templates
+from fastapi import FastAPI, Request, Form, Response
+from langchain.embeddings import SentenceTransformerEmbeddings
 
 os.environ["TRANSFORMERS_FORCE_CPU"] = "true"
 
@@ -36,7 +36,6 @@ llm = ChatGroq(
     api_key=api_key,
     )
 
-
 print("LLM Initialized....")
 
 prompt_template = """Use the following pieces of information to answer the user's question.

ingest.py

@@ -1,11 +1,9 @@
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.document_loaders import DirectoryLoader
-from langchain.document_loaders import PyPDFLoader
-from langchain.vectorstores import Qdrant
-from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain_community.document_loaders import DirectoryLoader
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.vectorstores import Qdrant
+from langchain_community.embeddings import SentenceTransformerEmbeddings
 
-# embeddings = SentenceTransformerEmbeddings(model_name='NeuML/pubmedbert-base-embeddings')
-# embeddings = SentenceTransformerEmbeddings(model_name='mixedbread-ai/mxbai-embed-large-v1')
 embeddings = SentenceTransformerEmbeddings(model_name='BAAI/bge-large-en')
 
 print(embeddings)