docs: polish and update

Signed-off-by: Chojan Shang <[email protected]>

Author: PsiACE

content/_index.md

@@ -26,7 +26,8 @@ date_format = "%b %-d, %Y"
 +++
 
 Hi, I'm **Chojan** (PsiACE).
-I lead GenAI platform work at Vesoft/NebulaGraph, serve on the Apache OpenDAL PMC, and previously helped build Databend from query execution to storage I/O.
+GenAI engineer at Vesoft (NebulaGraph), leading the NebulaGraph GenAI Platform and driving GraphRAG and agent workflows to production and standardization.
+PMC member at Apache OpenDAL, improving the unified storage interface for usability and stability.
+Previously a founding/core engineer at Databend, contributing to multiple core refactors and community documentation/tutorials.
 
-I care about predictable infrastructure, graph-native retrieval, and docs that scale contributors.
-Expect field notes on agent workflows, Fusion GraphRAG, and resilient data systems.
+I care about predictable infrastructure and open collaboration that scales contributors.

content/about/_index.md

@@ -13,29 +13,29 @@ comment = false
 reaction = false
 +++
 Hi, I'm **Chojan Shang** (aka **PsiACE**).
-I focus on engineering data and AI systems that are predictable, observable, and maintainable — not one-off demos.
+I focus on engineering data and AI systems with clear contracts, observable operations, and auditable workflows.
+Not one‑off demos, but maintainable and measurable product capabilities.
 
 ## Experience & Responsibilities
 
 **GenAI Engineer | Vesoft Inc. (NebulaGraph)**  
 2024.09 – present · Shanghai  
-- Deliver GraphRAG and Generative AI for graph-database scenarios across retrieval, Q&A, and recommendation.
-- Lead the architecture and engineering of the NebulaGraph GenAI Platform: ingest → retrieval (vector/graph) → inference; establish unified observability (latency, recall, hit rate).
-- Design and implement a Fusion GraphRAG framework that fuses structural graph knowledge with semantic retrieval; achieved ~30% faster time-to-first-use and ~15% precision uplift at the same compute.
-- Drive LLM engineering integration with the Nebula ecosystem (schema, data sync, auth/audit); codify reusable components and best practices to power QA and recommendation systems.
+- Deliver GraphRAG and generative AI in graph‑database scenarios across retrieval, Q&A, and recommendation.
+- Lead the architecture and engineering of the NebulaGraph GenAI Platform: ingest → retrieval (vector/graph) → inference.
+- Design and implement a Fusion GraphRAG framework that fuses structural graph knowledge with semantic retrieval to optimize context building for complex relational QA.
+- Advance LLM engineering workflows and codify reusable components and best practices.
 
 **PMC Member | Apache OpenDAL**  
 2022 – present · Remote  
-- Lead and contribute to the unified data access layer's architecture and releases; focus on caching, retries, observability, and multi-cloud backend abstraction.
-- Review critical PRs and design proposals; improve API consistency and platform stability; optimize data paths and metrics for high-concurrency / high-latency scenarios.
-- Build community norms and engineering standards; strengthen docs and test examples; mentor contributors and manage OSPP cadence; helped the project graduate to Apache TLP.
+- Contribute to and help lead the unified data access layer’s architecture and releases, focusing on caching, retries, observability, and multi‑cloud backend abstraction.
+- Review critical PRs and design topics, driving API consistency and platform stability; optimize data paths for high‑concurrency and high‑latency scenarios.
+- Build community norms and engineering standards, improve docs and examples, mentor contributors, and coordinate OSPP participation to improve contributor retention and release cadence.
 
-**Core Engineer | Databend Labs (cloud-native data warehouse)**  
+**Core Engineer | Databend Labs (cloud‑native data warehouse)**  
 2021.07 – 2024.08 · Remote  
-- Founding team member; built baseline query execution and storage access layers; unified I/O model around Apache Arrow/Parquet.
-- Led integrations with lakeFS and KubeSphere; delivered a unified access layer and caching for cloud-native data-lake scenarios.
-- Optimized execution and storage I/O to support high-throughput concurrent workloads; project stars grew from ~800 to 8000+ in three years.
-- Drove developer advocacy and community programs that turned Databend into a representative OSS data warehouse.
+- Founding team member; built baseline query execution and storage access layers; unified I/O around Apache Arrow/Parquet.
+- Led integrations and case studies with HuggingFace, lakeFS, and KubeSphere to broaden data‑lake/cloud‑native scenarios.
+- Drove developer advocacy and community operations; the project grew from ~800 to 8000+ stars in three years and became a representative OSS data warehouse.
 
 ## Focus Areas
 

content/posts/_index.md

@@ -1,6 +1,6 @@
 +++
-title = "Writing"
-description = "Field notes on agent protocols, graph-native retrieval, and resilient data systems."
+title = "Posts"
+description = "Notes on agent workflows, Fusion GraphRAG, and resilient data/AI platforms."
 sort_by = "date"
 template = "blog.html"
 page_template = "post.html"
@@ -11,7 +11,7 @@ generate_feeds = true
 lang = "en"
 
 title = "Latest Posts"
-subtitle = "Long-form updates on building production AI platforms, agent tooling, and graph intelligence."
+subtitle = "Long‑form on production GenAI platforms, agent tooling, and graph‑driven retrieval."
 
 date_format = "%b %-d, %Y"
 

content/posts/_index.zh.md

@@ -1,6 +1,6 @@
 +++
-title = "写作"
-description = "记录智能体协议、图检索与韧性数据系统的实践与思考。"
+title = "文章"
+description = "记录智能体工作流、Fusion GraphRAG 与韧性的数据/AI 平台。"
 sort_by = "date"
 template = "blog.html"
 page_template = "post.html"
@@ -11,7 +11,7 @@ generate_feeds = true
 lang = "zh"
 
 title = "最新文章"
-subtitle = "围绕可落地的 AI 基础设施、智能体工具链与图智能的长文记录。"
+subtitle = "围绕可落地的 GenAI 平台、智能体工具链与图驱动检索的长文。"
 
 date_format = "%Y年%m月%d日"