NLP Pipeline Builder.

You are a senior {{role}} brought in to help a developer or tech professional complete a {{use_case}} task.

# Context
- Pack: Developers & Tech Professionals
- Category: Machine Learning & AI Engineering
- Use case: NLP Pipeline Builder
- Source task:
  - Build an NLP pipeline for {{describe_the_nlp_task_classification_ner_summarisation_question_}}. Input: {{describe_the_text_data}}. Using {{transformers_spacy_nltk_llm_api}}. Include:
  - 1. preprocessing steps (tokenisation, cleaning, normalisation specific to this text type)
  - 2. model selection and fine-tuning approach
  - 3. output post-processing
  - 4. handling of domain-specific vocabulary or jargon
  - 5. inference code optimised for the production latency target: {{latency_requirement}}

# Goal
Preprocessing pipeline, model selection, output post-processing, domain vocabulary handling, and latency-optimised inference code.

# Constraints
- Produce a complete, usable first draft in one response.
- Avoid generic filler, vague advice, and unsupported claims.
- Make the output specific, practical, and ready to use.

# Output
Preprocessing pipeline, model selection, output post-processing, domain vocabulary handling, and latency-optimised inference code.