deploy rag

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.10
+
+WORKDIR /app
+
+COPY . .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,147 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from langchain_huggingface import HuggingFacePipeline
+
+app = FastAPI()
+
+
+# -----------------------
+# Schema Validation
+# -----------------------
+class Query(BaseModel):
+    question: str
+
+
+# -----------------------
+# Load documents
+# -----------------------
+
+loader = PyPDFLoader("seplat.pdf")
+docs = loader.load()
+
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size=1000,
+    chunk_overlap=200
+)
+
+doc_chunks = text_splitter.split_documents(docs)
+
+
+# -----------------------
+# Embedding Model
+# -----------------------
+
+embeddings = HuggingFaceEmbeddings(
+    model_name="all-MiniLM-L6-v2"
+)
+
+
+# -----------------------
+# Vectorstore
+# -----------------------
+
+db = Chroma.from_documents(
+    documents=doc_chunks,
+    embedding=embeddings,
+    persist_directory="./chroma_db"
+)
+
+retriever = db.as_retriever(
+    search_type="similarity",
+    search_kwargs={"k": 1}
+)
+
+
+# -----------------------
+# Prompt
+# -----------------------
+
+prompt_template = """
+You are an AI assistant for Obiex.
+Use ONLY the context below to answer the question.
+If the answer is not in the context, say you don't know.
+
+Context:
+{context}
+
+Question:
+{question}
+
+Answer:
+"""
+
+prompt = ChatPromptTemplate.from_template(prompt_template)
+
+
+# -----------------------
+# LLM
+# -----------------------
+
+model_name = "microsoft/phi-4-mini-instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    torch_dtype="auto"
+)
+
+text_gen_pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=256
+)
+
+llm = HuggingFacePipeline(pipeline=text_gen_pipe)
+
+
+# -----------------------
+# RAG chain
+# -----------------------
+
+rag_chain = (
+    {
+        "context": retriever,
+        "question": RunnablePassthrough()
+    }
+    | prompt
+    | llm
+    | StrOutputParser()
+)
+
+
+# -----------------------
+# API endpoint
+# -----------------------
+
+@app.post("/query")
+def query_rag(q: Query):
+    try:
+
+        docs = retriever.get_relevant_documents(q.question)
+        response = rag_chain.invoke(q.question)
+
+        return {
+            "question": q.question,
+            "answer": response,
+            "sources": [doc.metadata for doc in docs]
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/health")
+def health():
+    return {"status": "ok"}

requirements.txt

@@ -0,0 +1,12 @@
+fastapi
+uvicorn
+langchain
+langchain-community
+langchain-core
+langchain-huggingface
+chromadb
+sentence-transformers
+transformers
+accelerate
+pypdf
+tiktoken