Initial FastAPI RAG backend

.gitignore

@@ -1,207 +1,20 @@
-# Byte-compiled / optimized / DLL files
+# Python
 __pycache__/
-*.py[codz]
-*$py.class
+*.pyc
+*.pyo
+*.pyd
 
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py.cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# UV
-#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#uv.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-#poetry.toml
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
-#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
-#pdm.lock
-#pdm.toml
-.pdm-python
-.pdm-build/
-
-# pixi
-#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
-#pixi.lock
-#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
-#   in the .venv directory. It is recommended not to include this directory in version control.
-.pixi
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.envrc
-.venv
-env/
+# Virtual environment
 venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
 
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-
-# Abstra
-# Abstra is an AI-powered process automation framework.
-# Ignore directories containing user credentials, local state, and settings.
-# Learn more at https://abstra.io/docs
-.abstra/
-
-# Visual Studio Code
-#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
-#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
-#  you could uncomment the following to ignore the entire vscode folder
-# .vscode/
-
-# Ruff stuff:
-.ruff_cache/
-
-# PyPI configuration file
-.pypirc
+# Environment variables
+.env
 
-# Cursor
-#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
-#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
-#  refer to https://docs.cursor.com/context/ignore-files
-.cursorignore
-.cursorindexingignore
+# Vector store & runtime data
+data/
+*.npy
+*.index
 
-# Marimo
-marimo/_static/
-marimo/_lsp/
-__marimo__/
+# OS / editor
+.vscode/
+.DS_Store

main.py

@@ -0,0 +1,75 @@
+import os
+from fastapi import FastAPI
+from pydantic import BaseModel
+from dotenv import load_dotenv
+import google.generativeai as genai
+from rag_store import search_knowledge
+
+load_dotenv()
+
+genai.configure(api_key=os.getenv("GEMINI_API_KEY"))
+
+app = FastAPI(title="AI RAG Backend with Gemini")
+
+class PromptRequest(BaseModel):
+    prompt: str
+
+@app.get("/")
+def home():
+    return {"message": "AI backend is running 🚀"}
+
+@app.post("/ask")
+async def ask(data: PromptRequest):
+    results = search_knowledge(data.prompt)
+
+    if not results:
+        return {
+            "answer": "I don't know based on the provided documents.",
+            "confidence": 0.0,
+            "citations": []
+        }
+
+    # -------- Context
+    context_text = "\n".join(r["text"] for r in results)
+
+    prompt = f"""
+Answer the question strictly using the context.
+If unsure, say "I don't know".
+
+Question:
+{data.prompt}
+
+Context:
+{context_text}
+"""
+
+    model = genai.GenerativeModel("gemini-2.5-flash")
+    response = model.generate_content(prompt)
+
+    # -------- Confidence scoring
+    avg_distance = sum(r["distance"] for r in results) / len(results)
+
+    if avg_distance < 0.6:
+        confidence = 0.9
+    elif avg_distance < 1.2:
+        confidence = 0.7
+    else:
+        confidence = 0.4
+
+    # -------- Citations
+    citations = []
+    seen = set()
+    for r in results:
+        key = (r["metadata"]["source"], r["metadata"]["page"])
+        if key not in seen:
+            seen.add(key)
+            citations.append({
+                "source": r["metadata"]["source"],
+                "page": r["metadata"]["page"]
+            })
+
+    return {
+        "answer": response.text,
+        "confidence": round(confidence, 2),
+        "citations": citations
+    }

rag_store.py

@@ -0,0 +1,67 @@
+import os
+import faiss
+import numpy as np
+from sentence_transformers import SentenceTransformer
+from pypdf import PdfReader
+
+DATA_DIR = "data"
+INDEX_FILE = "vector.index"
+DOCS_FILE = "documents.npy"
+META_FILE = "metadata.npy"
+
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+# -------------------------
+# Load or build index
+# -------------------------
+if os.path.exists(INDEX_FILE):
+    print("🔁 Loading FAISS index from disk...")
+    index = faiss.read_index(INDEX_FILE)
+    documents = np.load(DOCS_FILE, allow_pickle=True)
+    metadata = np.load(META_FILE, allow_pickle=True)
+else:
+    print("🧠 Building FAISS index...")
+    texts = []
+    meta = []
+
+    for file in os.listdir(DATA_DIR):
+        if file.endswith(".pdf"):
+            reader = PdfReader(os.path.join(DATA_DIR, file))
+            for i, page in enumerate(reader.pages):
+                text = page.extract_text()
+                if text:
+                    texts.append(text)
+                    meta.append({
+                        "source": file,
+                        "page": i + 1
+                    })
+
+    embeddings = model.encode(texts)
+    index = faiss.IndexFlatL2(embeddings.shape[1])
+    index.add(np.array(embeddings))
+
+    np.save(DOCS_FILE, texts)
+    np.save(META_FILE, meta)
+    faiss.write_index(index, INDEX_FILE)
+
+    documents = texts
+    metadata = meta
+
+    print("✅ FAISS index saved to disk.")
+
+# -------------------------
+# Search
+# -------------------------
+def search_knowledge(query, top_k=5):
+    query_vec = model.encode([query])
+    distances, indices = index.search(query_vec, top_k)
+
+    results = []
+    for dist, idx in zip(distances[0], indices[0]):
+        results.append({
+            "text": documents[idx],
+            "metadata": metadata[idx],
+            "distance": float(dist)
+        })
+
+    return results

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn
+python-dotenv
+google-generativeai
+faiss-cpu
+sentence-transformers
+pypdf
+numpy