Enterprise-Grade Conversational Intelligence: A Domain-Aware Chatbot Framework using Gpt-3.5, Langchain, And Rag with Local Vector Indexing
Bibliographic record
Abstract
This thesis presents a scalable and domain-aware chatbot framework that integrates GPT-3.5 with LangChain and Retrieval-Augmented Generation (RAG) to deliver context-sensitive responses grounded in enterprise-specific knowledge. The proposed architecture leverages local vector databases, including FAISS and Chroma, to perform efficient semantic retrieval from proprietary document repositories. By embedding domain documents into high-dimensional vector space and linking them with transformer-based query models, the system retrieves relevant context passages in real time, enhancing the language model's relevance and accuracy. LangChain orchestrates the interaction between the language model and retrieval components, enabling modular and extensible prompt chains tailored to organizational needs. The framework supports document ingestion in varied formats, including PDFs, Word documents, and structured CSV files, converting them into persistent embeddings for rapid querying. Security and data privacy are maintained through localized storage, ensuring compliance with enterprise governance standards. Experimental evaluations demonstrate significant improvements in factual consistency and contextual relevance across test scenarios in finance, legal, and customer support domains. This work underscores the potential of combining generative AI with vector-based retrieval to build intelligent, responsive assistants for domain-specific enterprise applications
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.009 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".