Upload 3 files

Dockerfile

@@ -0,0 +1,48 @@
+# FROM ollama/ollama
+
+# COPY ./run-ollama.sh /tmp/run-ollama.sh
+# COPY ./Modelfile /tmp/Modelfile
+
+
+# WORKDIR /tmp
+
+# RUN chmod +x run-ollama.sh 
+
+# RUN ./run-ollama.sh
+
+# FROM python:3.10.12 AS build
+
+# RUN useradd -m -u 1000 user
+# WORKDIR /app
+
+# COPY --chown=user ./requirements.txt requirements.txt
+# RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# COPY --chown=user . /app
+
+# USER user 
+
+# ENV HOME=/home/user \
+# 	PATH=/home/user/.local/bin:$PATH
+
+# CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+FROM python:3.10.12
+
+RUN curl -fsSL https://ollama.com/install.sh | sh
+
+RUN useradd -m -u 1000 user
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+COPY ./Modelfile /Modelfile
+
+COPY --chown=user . /app
+
+USER user 
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app1.py

@@ -0,0 +1,44 @@
+import os
+import re
+from langchain_chroma import Chroma
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains import RetrievalQA
+from langchain_community.document_loaders import TextLoader, Docx2txtLoader
+from langchain.prompts import PromptTemplate
+from langchain_ollama import OllamaLLM
+import subprocess
+import threading
+import time
+
+model_name = "qwen2.5:3b"
+
+def ollama_service_thread():
+    subprocess.run("ollama serve", shell=True)
+
+OLLAMA_SERVICE_THREAD = threading.Thread(target=ollama_service_thread)
+OLLAMA_SERVICE_THREAD.start()
+
+print("Giving ollama serve a moment")
+time.sleep(10)
+
+subprocess.run(f"ollama pull {model_name}", shell=True)
+
+
+
+
+model = OllamaLLM(model="qwen2.5:3b")
+
+
+from fastapi import FastAPI
+
+app = FastAPI()
+
+@app.get("/")
+def greet_json():
+    response_text2 = model.invoke('hi')
+    x1 = subprocess.run(f"ollama show qwen2.5:3b",  capture_output = True,shell=True)
+    return {"Hello1": f"{x1}",
+            "Hello1": f"{response_text2}",
+            
+           }

requirements.txt

@@ -0,0 +1,9 @@
+langchain-community
+langchain
+transformers
+langchain_huggingface
+langchain-chroma
+langchain_ollama
+docx2txt
+fastapi
+uvicorn[standard]