Upload 4 files

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.10
+
+WORKDIR /app
+COPY . .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+ENV PORT=7860
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,31 @@
+from fastapi import FastAPI, Query
+from langchain_community.vectorstores import Chroma
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from together import Together
+import os
+
+embedding = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+vectordb = Chroma(persist_directory="chroma_db", embedding_function=embedding)
+
+TOGETHER_API_KEY = os.getenv("TOGETHER_API_KEY", "")
+client = Together(api_key=TOGETHER_API_KEY)
+
+def call_llama(prompt: str):
+    response = client.chat.completions.create(
+        model="meta-llama/Llama-3-8b-chat-hf",
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": prompt}
+        ]
+    )
+    return response.choices[0].message.content
+
+app = FastAPI()
+
+@app.get("/ask")
+async def ask(q: str = Query(..., description="Your question")):
+    docs = vectordb.similarity_search(q, k=3)
+    context = "\n".join([doc.page_content for doc in docs])
+    final_prompt = f"Use the context below to answer the question.\n\nContext:\n{context}\n\nQuestion: {q}"
+    answer = call_llama(final_prompt)
+    return {"answer": answer}

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn
+langchain
+together
+chromadb
+sentence-transformers
+langchain-community
+pymupdf

upload_pdf.py

@@ -0,0 +1,26 @@
+import os
+from fastapi import FastAPI, File, UploadFile
+from langchain_community.document_loaders import PyMuPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import Chroma
+
+app = FastAPI()
+
+@app.post("/upload")
+async def upload_pdf(file: UploadFile = File(...)):
+    file_location = f"uploads/{file.filename}"
+    with open(file_location, "wb") as f:
+        f.write(await file.read())
+
+    loader = PyMuPDFLoader(file_location)
+    docs = loader.load()
+
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    chunks = splitter.split_documents(docs)
+
+    embedding = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+    vectordb = Chroma.from_documents(chunks, embedding, persist_directory="chroma_db")
+    vectordb.persist()
+
+    return {"message": f"✅ {file.filename} uploaded and processed into vector DB."}