During my internship at a software services company, I noticed a recurring problem: technicians spent hours searching through hundreds of pages of PDF manuals to answer client questions. The company deploys a suite of management tools accounting, HR, logistics mainly to public institutions managing projects funded by international donors.
I kept thinking: this is exactly the kind of problem LLMs were made for. So for my Master's project in AI & Big Data, I built an intelligent assistant to handle it.
The constraint that shaped every technical decision: no data could leave the local infrastructure. These institutions handle sensitive financial data it cannot be sent to OpenAI, Anthropic, or any cloud provider.
This forced me into the world of fully local LLMs. Here's what I built, what broke, and what I learned.
The company had accumulated massive technical documentation PDF manuals, configuration guides, FAQ files but no efficient way to query it. When a technician faced an issue with the accounting module or the HR module, they searched manually. Slow, inconsistent, and dependent on individual expertise.
Classic LLMs can't help here: they don't know the private internal documentation. And without grounding in official docs, they hallucinate procedures dangerous when dealing with accounting operations for donor-funded projects.
The solution: RAG (Retrieval-Augmented Generation) make the LLM answer only from the official documentation, injected at query time.
Before the code, the concept in one sentence: instead of asking the LLM to "know" everything, you retrieve the relevant passages from your documents and inject them into the prompt as context.
The pipeline has two distinct phases:
Phase 1 : Ingestion (done once)
PDF documents
↓
Chunking (split into 300-character blocks)
↓
Embedding (convert each block to a vector)
↓
ChromaDB (store all vectors)
Phase 2 : Query (at each question)
User question
↓
Embed the question (same model)
↓
ChromaDB similarity search → top 3 chunks
↓
Inject chunks + question into LLM prompt
↓
Llama 3 generates a grounded answer
The key insight: the LLM never "knows" your documents. It reads them fresh at each query, from the context you provide. No fine-tuning needed. No retraining when docs are updated.
Everything runs locally via Docker Compose. Four services, each with a clear role:
| Service | Role | Port |
|---|---|---|
| Ollama | ||
| Runs Llama 3 locally | 11434 | |
| ChromaDB | ||
| Vector database | 8001 | |
| FastAPI | ||
| RAG pipeline + REST API | 8000 | |
| Streamlit | ||
| User interface | 8501 |
services:
ollama:
image: ollama/ollama:latest
ports: ["11434:11434"]
volumes: ["./ollama_models:/root/.ollama"]
environment:
- OLLAMA_KEEP_ALIVE=24h
chromadb:
image: chromadb/chroma:latest
ports: ["8001:8000"]
volumes: ["./chroma_db:/chroma/chroma"]
python-api:
build: ./src
ports: ["8000:8000"]
depends_on: [ollama, chromadb]
environment:
- OLLAMA_BASE_URL=http://ollama:11434
- CHROMA_HOST=chromadb
- CHROMA_PORT=8000
I ingested 10 documents accounting references (SYSCOHADA, SYCEBNL), a general accounting code, and internal user manuals. That's 2,111 pages split into 9,669 chunks.
import os
import chromadb
from langchain_community.document_s import PyPDF
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_chroma import Chroma
from langchain_community.embeddings import HuggingFaceEmbeddings
DATA_DIR = "/app/data/documents"
COLLECTION_NAME = "documentation"
def load_documents():
documents = []
for fichier in os.listdir(DATA_DIR):
if fichier.endswith(".pdf"):
try:
= PyPDF(os.path.join(DATA_DIR, fichier))
docs = .load()
for doc in docs:
doc.metadata["module"] = fichier.replace(".pdf", "")
documents.extend(docs)
except Exception as e:
print(f"Skipped {fichier}: {e}") # Don't crash on encrypted PDFs
return documents
def store_embeddings(chunks):
embeddings = HuggingFaceEmbeddings(
model_name="all-MiniLM-L6-v2",
model_kwargs={"device": "cpu"}
)
client = chromadb.HttpClient(host="chromadb", port=8000)
Chroma.from_documents(
documents=chunks,
embedding=embeddings,
collection_name=COLLECTION_NAME,
client=client
)
print(f"Done — {len(chunks)} vectors stored")
Two things worth noting:
try/except
is not optional one encrypted PDF (it happened) would have crashed the entire ingestion without it. Install cryptography
if you hit an AES error: pip install cryptography
import chromadb
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.llms import Ollama
from langchain_chroma import Chroma
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser
def create_rag_chain():
embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
client = chromadb.HttpClient(host="chromadb", port=8000)
vectorstore = Chroma(
client=client,
collection_name="documentation",
embedding_function=embeddings
)
retriever = vectorstore.as_retriever(
search_type="similarity",
search_kwargs={"k": 3}
)
llm = Ollama(
base_url="http://ollama:11434",
model="llama3",
temperature=0.3,
num_predict=250 # Cap response length — critical on CPU
)
template = """You are a technical support assistant.
Answer ONLY from the provided context. Cite your source.
If the answer is not in the context, say so clearly.
Context: {context}
Question: {question}
Answer:"""
prompt = ChatPromptTemplate.from_template(template)
def format_docs(docs):
return "\n\n".join([
f"[Source: {d.metadata.get('module', '?')}]\n{d.page_content}"
for d in docs
])
return (
{"context": retriever | format_docs, "question": RunnablePassthrough()}
| prompt
| llm
| StrOutputParser()
)
The chain is a pipeline: retriever → prompt → llm → parser
. LangChain's |
operator makes this clean and readable. Each step passes its output to the next.
FastAPI exposes the chain as a REST endpoint:
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from rag_chain import create_rag_chain
app = FastAPI(title="Local RAG Assistant")
chain = create_rag_chain()
class QueryRequest(BaseModel):
question: str
@app.post("/query")
def query(request: QueryRequest):
try:
answer = chain.invoke(request.question)
return {"question": request.question, "answer": answer}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
Streamlit makes it usable in a browser in 10 lines:
import streamlit as st
import requests
st.title("Technical Support Assistant")
question = st.text_input("Your question:")
if st.button("Search") and question:
with st.spinner("Searching documentation... (1-2 min on CPU)"):
r = requests.post(
"http://python-api:8000/query",
json={"question": question},
timeout=600
)
st.write(r.json()["answer"])
This is the part nobody writes about. Three real problems I hit.
I was connecting with the old client_settings
syntax:
Chroma.from_documents(
documents=chunks,
client_settings=Chroma.Settings(chroma_server_host="chromadb")
)
The ingestion ran without errors, showed 9669 chunks stored but ChromaDB had 0 vectors. Querying returned nothing.
The fix explicit HttpClient
:
client = chromadb.HttpClient(host="chromadb", port=8000)
Chroma.from_documents(documents=chunks, client=client, ...)
Also: the v1 heartbeat endpoint (/api/v1/heartbeat
) is deprecated. Use /api/v2/heartbeat
to check if ChromaDB is alive.
from langchain.prompts import ChatPromptTemplate # ❌ ModuleNotFoundError
from langchain.schema.runnable import RunnablePassthrough # ❌ ModuleNotFoundError
from langchain_core.prompts import ChatPromptTemplate # ✅
from langchain_core.runnables import RunnablePassthrough # ✅
LangChain has been refactoring aggressively across versions. If you hit ModuleNotFoundError
, check langchain_core
first it's the stable base layer they're committing to not break.
Llama 3 (8B parameters) on CPU generates roughly 2-5 tokens per second. A 200-word answer takes 2+ minutes. My 120-second timeout was too short.
Three things helped significantly:
k
from 5 to 3 chunks shorter prompt = faster time-to-first-tokennum_predict=250
to cap response length without it, the model generates forever.wslconfig
on Windows to avoid swapAfter setup, the assistant correctly answers questions grounded in the official documentation:
And critically when the answer isn't in the documentation, it says so explicitly instead of hallucinating. That was the whole point.
On RAG:
The embedding model used during ingestion must be identical to the one used at query time. A different model produces incompatible vector spaces your similarity search returns garbage without any error message.
Chunk size matters more than expected. 500 characters worked less well than 300 for technical documents shorter chunks produce more precise retrieval.
Metadata on chunks is essential for source citation. Tag every chunk with its document name at ingestion time.
On local LLMs:
Running on CPU is slow but viable for non-real-time use cases like internal support tools.
num_predict
is your most important parameter for performance. Without it, the model generates until it decides to stop sometimes never.
Docker container networking does not use localhost
. Use the service name defined in docker-compose.yml
(e.g., chromadb
, ollama
) as the hostname when connecting between containers.
This project is available on my github : https://github.com/josaphatstar/Assistant-Intelligent-RAG
This RAG pipeline handles straightforward questions well. But it has a core limitation: it always does the same thing regardless of the question type. Whether you ask a procedural question or report a system crash, it searches the docs and answers. No reasoning about what strategy fits best.
In the next article, I'll show how I evolved this into an Agentic AI architecture with LangGraph where the system first decides which agent to call (documentation search, error diagnosis, or human escalation ticket), then acts accordingly.
I'm a Master's student in AI & Big Data, and this project came out of a real internship constraint no cloud, no API keys, just local infrastructure and open-source tools. I'm curious: have you built a local RAG pipeline under similar constraints? What stack did you use, and what broke first? Drop it in the comments I'd genuinely like to compare notes.