Is the training Qualiopi certified?

Yes, Learni is a Qualiopi-certified training organization. This certification guarantees the quality of our courses and enables funding through OPCO and other mechanisms.

How can I fund my training?

Our courses are eligible for OPCO funding. Learni supports you through the funding process. A personalized quote is available upon request.

What are the prerequisites for this training?

The prerequisites for the Training DSPy - Optimizing Intelligent LLM Pipelines training are: Advanced proficiency in Python, LLM APIs (OpenAI, HuggingFace), chain-of-thought prompting. A preliminary interview validates your eligibility.

Is the training available in person?

Yes, the Training DSPy - Optimizing Intelligent LLM Pipelines training is available in distanciel. The format can be adapted to your needs (inter, intra, custom).

Training DSPy - Optimizing Intelligent LLM… | Learni

The story of Learni

Founded by passionate advocates of learning and innovation, Learni set out to make professional training accessible to everyone, everywhere in the world. Our team works in the largest cities such as Paris, Lyon, Marseille, and internationally, to support talents and organizations in their skills development.

Configure your training

Response within 24hNo commitment100% free

9 spots remaining for the next session

FormatParticipantsDateDetails

Which format do you prefer?

Methods, approaches, and teaching resources

The Training DSPy - Optimizing Intelligent LLM Pipelines training is delivered in-person or remotely (blended-learning, e-learning, virtual classroom, remote in-person). At Learni, a Qualiopi-certified training organization, each program is designed to maximize skills acquisition, regardless of the training mode chosen.

The trainer alternates between demonstrative, interrogative, and active methods (through practical exercises and/or real-world scenarios). This pedagogical approach ensures concrete and directly applicable learning in the workplace.

Teaching resources provided

To ensure the quality of the Training DSPy - Optimizing Intelligent LLM Pipelines training, Learni provides the following teaching resources:

Mac or PC computers, high-speed fiber internet, whiteboard or flipchart, video projector or interactive touchscreen (for remote sessions)
Training environments installed on workstations or accessible online
Course materials, practical exercises, and supplementary resources
Post-training access to materials and teaching resources

For in-house training at a location external to Learni, the client ensures and commits to having all necessary teaching materials (IT equipment, internet connection...) for the proper conduct of the training action in accordance with the prerequisites indicated in the communicated training program.

* contact us for remote feasibility** ratio varies depending on the training followed

Assessment methods

The assessment of skills acquired during the Training DSPy - Optimizing Intelligent LLM Pipelines training is carried out through:

During training: case studies, practical exercises, and professional scenarios
At the end of training: self-assessment questionnaire and skills evaluation by the trainer
After training: training completion certificate detailing acquired skills

Training accessibility

Learni is committed to the accessibility of its professional training programs. All our training programs are accessible to people with disabilities. Our teams are available to adapt teaching methods to your specific needs. Do not hesitate to contact us for any accommodation request.

Training access terms and deadlines

Training objectives

Master the DSPy architecture to develop professional AI pipelines

Design optimized DSPy signatures and modules for enterprise use

Implement automatic optimizers for certifiable LLM prompts

Develop multi-stage programs with advanced metric evaluation

Deploy scalable DSPy pipelines connected to databases

Optimize AI performance to reduce costs and latency in production

Training program

Module 1DSPy Fundamentals: Advanced Signatures and Modules (Python, LLMs, Assertions)

Expert installation of DSPy with integration of LLMs such as GPT-4 and Llama, definition of precise signatures for complex tasks, creation of custom modules with metric assertions, hands-on exercises on semantic classification, development of a first DSPy program tested in real-time, production of a functional deliverable with trainer code review.

Module 2DSPy Programs: Chains and Modular Composition (Tracing Tools, Debugging)

Design of multi-module DSPy chains for RAG and question-answering, use of integrated tracing tools to debug pipelines, exercises on dynamic program composition, real business case with actual data, iterative prompt optimization via execution loops, generation of performance reports and live adjustments for immediate efficiency.

Module 3DSPy Optimizers: BootstrapFewShot and MIPRO (Metrics, Auto-Generated Datasets)

In-depth exploration of optimizers like BootstrapFewShot and MIPRO for automatic tuning, configuration of LLM-synthesized few-shot datasets, hands-on exercises optimizing 10 prompts in 30 minutes, evaluation with custom metrics (F1-score, ROUGE), enterprise use case on entity extraction, production of production-ready optimizers with cross-validation.

Module 4Complex DSPy Pipelines: Advanced RAG and Agents (Vector Stores, LangChain Hybrid)

Development of optimized RAG pipelines with DSPy and vector stores (FAISS, Pinecone), integration of multi-tool agents for hybrid tasks, exercises on DSPy-LangChain hybridization, simulation of enterprise scenarios with 100k documents, robustness tests against noisy data, creation of deployable deliverables including advanced monitoring and logging.

Module 5DSPy Deployment and Scaling: Production, Monitoring (Docker, API Endpoints, LLM Costs)

Containerization of DSPy pipelines with Docker and deployment on cloud (AWS, Vercel), LLM cost optimization via caching and batching, final exercises on secure REST APIs, monitoring with Prometheus and Grafana, real enterprise cases for scaling to 1M requests/day, completion of red thread project with full audit and strategic evolution plan.