Remove legacy storage implementations and deprecated examples: - Delete FAISS, JSON, Memgraph, Milvus, MongoDB, Nano Vector DB, Neo4j, NetworkX, Qdrant, Redis storage backends - Remove Kubernetes deployment manifests and installation scripts - Delete unofficial examples for deprecated backends and offline deployment docs Streamline core infrastructure: - Consolidate storage layer to PostgreSQL-only implementation - Add full-text search caching with FTS cache module - Implement metrics collection and monitoring pipeline - Add explain and metrics API routes Modernize frontend and tooling: - Switch web UI to Bun with bun.lock, remove npm and pnpm lockfiles - Update Dockerfile for PostgreSQL-only deployment - Add Makefile for common development tasks - Update environment and configuration examples Enhance evaluation and testing capabilities: - Add prompt optimization with DSPy and auto-tuning - Implement ground truth regeneration and variant testing - Add prompt debugging and response comparison utilities - Expand test coverage with new integration scenarios Simplify dependencies and configuration: - Remove offline-specific requirement files - Update pyproject.toml with streamlined dependencies - Add Python version pinning with .python-version - Create project guidelines in CLAUDE.md and AGENTS.md
27 lines
No EOL
1.1 KiB
Text
27 lines
No EOL
1.1 KiB
Text
---Task---
|
||
Answer the query using ONLY the provided context. Do NOT add any information that is not explicitly present.
|
||
|
||
STRICT GUIDELINES
|
||
- Every statement must be directly supported by the context. If the exact fact, number, date, or name is not found, answer “not specified in available information”.
|
||
- Cite the specific chunk of {context_data} for each factual claim (citations will be added automatically).
|
||
- If any part of the question is not covered, explicitly state which part is missing.
|
||
- Do not infer, extrapolate, or generalize beyond the given text.
|
||
|
||
RELEVANCE GUIDELINES
|
||
- Mirror the wording of the question: use the same key terms and structure when answering.
|
||
- Address each component of the question in the order presented.
|
||
- For multiple sub‑questions, provide separate short answers for each, still grounded in the context.
|
||
|
||
FORMAT
|
||
- Use the same language as the question.
|
||
- Use Markdown for readability.
|
||
- Do NOT include manual citation markers or a References section (they will be added automatically).
|
||
- Output type: {response_type}
|
||
{coverage_guidance}
|
||
|
||
Question: {user_prompt}
|
||
|
||
---Context---
|
||
{context_data}
|
||
|
||
Answer: |