HCLTech vs Chroma

HCLTech Newsroom: HCLSoftware to Acquire Robotiq.ai, HCLTech launches AI-powered wealth study, M Group selects HCLTech for AI-led IT transformation, and more

HCLTech's newsroom features multiple press releases: HCLSoftware to acquire Robotiq.ai to enhance HCL UnO Agentic; HCLTech launches first-of-its-kind AI-powered study for wealth management; M Group selects HCLTech for AI-led IT transformation across 200+ locations; HCLTech named Leader in Everest Group's PLM Services PEAK Matrix; HCLTech launches The Silicon Shift report; HCLTech launches HCLTech Pulse; HCLTech named Leader in ISG Procurement Services; HCLTech and CrowdStrike expand partnership; HCLFoundation and UP government extend partnership.

HCLTech launches Advanced Semiconductor Lab with Rs. 185 crore investment

The Bengaluru facility strengthens India’s position in the global chip ecosystem and is set to drive semiconductor innovation. Also, HCLTech and Transport for NSW to explore AI-powered traffic insights for India.

The Customer Trust Framework Brands Will Need to Make AI Pay Off

This article from CMSWire discusses why only 18% of brands see revenue impact from AI adoption, attributing the gap to customer trust rather than technology. It introduces the 'Triangle of Trust' framework—authenticity, logic, and empathy—coined by Harvard Business School professors Frances Frei and Anne Morris as a method to build trust in AI-driven customer experiences. The author advises brands to beta test AI tools with a smaller customer group before scaling and to incorporate human-like, empathetic interactions to accelerate trust. The piece cites an HCLTech report and offers practical steps for brands to close the AI revenue gap.

• Only 18% of brands report seeing revenue impact from AI investments, according to an HCLTech report.
• The Triangle of Trust framework consists of authenticity, logic, and empathy.
• The framework was coined by Harvard Business School professor Frances Frei and Anne Morris.

AI Agents Need Vector Databases for Memory

This technical blog post explains why retrieval-backed long-term memory for AI agents is best implemented with vector databases. It defines three memory types (working, long-term, episodic), outlines the memory stack (embedding model, vector store, chunking, metadata), recommends practical tooling (pgvector, Qdrant, Chroma) and embedding-dimension trade-offs, and provides a minimal Python example using pgvector and OpenAI embeddings. The author lists common production failure modes (stale memory, poor chunking, blind cosine similarity, context overflow, cost, privacy, and silent quality rot) and a practitioner's checklist for safe, private, and maintainable memory-enabled agents.

• Vector databases enable retrieval-backed long-term memory for agents by returning semantically similar chunks via embeddings and ANN search.
• Author recommends tooling trade-offs: pgvector (Postgres extension) for most production cases, Qdrant for heavy metadata filtering/scale, and Chroma for quick prototypes.
• Embedding dimension and model choice trade quality against cost; 768 dimensions is suggested as a sane production default.

Local RAG Evolved into Agentic AI with LangGraph

A developer describes converting a locally hosted RAG assistant (built with Ollama, ChromaDB, LangChain, Docker) into an agentic AI architecture using LangGraph. The author introduces a shared AgentState contract and implements three single-purpose agents — a RAG agent for documentation lookup, a Diagnostic agent with a fast known-error lookup and LLM fallback, and an Escalation agent that generates structured tickets when human intervention is required. An orchestrator uses a classifier to route queries conditionally through a state graph. The article discusses design lessons (classifier fragility, embedding initialization overhead, hardcoded escalation thresholds) and recommends starting with RAG and adding agents where needed.

• Author converted a local RAG assistant into an agentic AI architecture using LangGraph.
• The original local stack included Ollama, ChromaDB, LangChain, all running in Docker.
• The solution defines a shared AgentState TypedDict that agents read and update (fields include messages, question, plan, past_steps, response, next_agent, niveau_support).

Local RAG Assistant with Ollama, ChromaDB, LangChain

A Master's student built a local Retrieval-Augmented Generation (RAG) assistant to let technicians query private PDF manuals without sending data to cloud providers. The pipeline uses 300-character chunking, all-MiniLM-L6-v2 embeddings stored in ChromaDB, retrieval of the top 3 chunks, and local Llama 3 inference via Ollama. The system runs as four Docker Compose services (Ollama, ChromaDB, FastAPI, Streamlit). The author documents three practical failures and fixes: ChromaDB v2 silently storing data without an explicit HttpClient, LangChain refactoring into langchain_core, and slow Llama 3 CPU inference (mitigated by reducing retrieved chunks, capping responses with num_predict, and adding RAM). The project is open-source on GitHub and the author plans to evolve the pipeline toward an agentic architecture.

• Built a fully local RAG assistant using Ollama (Llama 3), ChromaDB, LangChain, FastAPI, and Streamlit, deployed via Docker Compose.
• Ingested 2,111 PDF pages split into 9,669 chunks using 300-character chunking and embedded with all-MiniLM-L6-v2.
• ChromaDB v2 required an explicit chromadb.HttpClient(host='chromadb', port=8000); old client_settings caused vectors to be silently not stored and /api/v2/heartbeat is the current health endpoint.