rag

.gitignore

@@ -0,0 +1,181 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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
+.venv
+env/
+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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# 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

.python-version

@@ -0,0 +1 @@
+3.11

app.py

@@ -1,6 +1,55 @@
 from fastapi import FastAPI
+from langchain_core.prompts import PromptTemplate
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_core.messages import HumanMessage
+import os
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from typing import List, Optional
+from rag import retrieve_context
+# RAG LLM setup
+llm_rag = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0.5)
+
+prompt = PromptTemplate.from_template(
+    "you are rag bot designed to answer questions on aakash jammula "
+    "(document contains my information/resume) and be engaging and only respond in text "
+    "like a human. Use context only when they ask about me (aakash jammula).\n\n"
+    "Context:\n{context}\n\nQuestion:\n{question}\nAnswer:"
+)
+
+
 app = FastAPI()
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
 
 @app.get("/")
 def read_root():
     return {"hello": "world"}
+
+
+
+class Query(BaseModel):
+    q: str
+    k: int = 5
+
+@app.post("/ask")
+async def ask(req: Query):
+    if not req.q:
+        raise HTTPException(status_code=400, detail="Missing question text")
+    context = retrieve_context(req.q, k=req.k)
+    user_prompt = prompt.invoke({"context": context, "question": req.q})
+    resp = llm_rag.invoke(user_prompt)
+    return {"context": context, "answer": resp.content}
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(
+        app,
+        host="0.0.0.0",
+        port=int(os.getenv("PORT", 5000))
+    )

pyproject.toml

@@ -0,0 +1,18 @@
+[project]
+name = "backend-port"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "fastapi>=0.115.12",
+    "hf-xet>=1.1.2",
+    "langchain-core>=0.3.60",
+    "langchain-google-genai>=2.1.4",
+    "langchain-huggingface>=0.2.0",
+    "langchain-pinecone>=0.2.6",
+    "pinecone>=6.0.2",
+    "python-dotenv>=1.1.0",
+    "python-multipart>=0.0.20",
+    "uvicorn>=0.34.2",
+]

rag.py

@@ -0,0 +1,28 @@
+# rag.py
+import os
+from dotenv import load_dotenv
+from pinecone import Pinecone, ServerlessSpec
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_pinecone import PineconeVectorStore
+
+load_dotenv()
+
+# Initialize Pinecone
+pc = Pinecone(api_key=os.getenv("PINECONE_API_KEY"))
+index_name = "resume-index"
+if not pc.has_index(index_name):
+    pc.create_index(
+        name=index_name,
+        dimension=384,
+        metric="cosine",
+        spec=ServerlessSpec(cloud="aws", region="us-east-1"),
+    )
+pinecone_index = pc.Index(index_name)
+
+# Embeddings + VectorStore
+embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+vectorstore = PineconeVectorStore(index=pinecone_index, embedding=embeddings)
+
+def retrieve_context(question: str, k: int = 5) -> str:
+    docs = vectorstore.similarity_search(question, k=k)
+    return "\n\n".join(d.page_content for d in docs)

requirements.txt

@@ -1,2 +1,10 @@
 uvicorn
-fastapi
+fastapi
+python-dotenv
+pinecone
+langchain_huggingface
+langchain_pinecone
+langchain_google_genai
+python-multipart
+langchain-core
+hf_xet