v1.4.8

## Import Notes

1. **Introduced a raw data query API** `/query/data`, enabling developers to retrieve complete raw data recalled by LightRAG for fine-grained processing.
2. Optimized the system to efficiently handle hundreds of documents and hundreds of thousands of ten-relationships in one batch job, resolving UI lag and enhancing overall system stability.
3. Drop entities with short numeric names that negatively impact performance and query results; dropping names containing only two digits, names shorter than six characters, and names mixed with digits and dots, like 1.1, 12.3, 1.2.3 etc. 
4. **Significantly improves the quantity and quality of entity and relation extraction for smaller parameter models, leading to a substantial improvement in query performance**
5. Optimized the prompt engineering for `Qwen3-30B-A3B-Instruct` and `gpt-oss-120b` models, incorporating targeted fault tolerance for model outputs. 
6. Implemented  `max tokens` and `tempreture` configuration to **prevent excessively long or endless output loop** during the entity relationship extraction phase for Large Language Model (LLM) responses. 

```
# Increased temperature values may mitigate infinite inference loops in certain LLM, such as Qwen3-30B.
OPENAI_LLM_TEMPERATURE=0.9

# For vLLM/SGLang doployed models, or most of OpenAI compatible API provider
OPENAI_LLM_MAX_TOKENS=9000

# For Ollama Deployed Modeles
OLLAMA_LLM_NUM_PREDICT=9000

# For OpenAI o1-mini or newer modles
OPENAI_LLM_MAX_COMPLETION_TOKENS=9000
```

> The purpose of setting max tokens parameter is to truncate LLM output before timeouts occur, thereby preventing document extraction failures. This addresses issues where certain text blocks (e.g., tables or citations) containing numerous entities and relationships can lead to overly long or even endless loop outputs from LLMs. This setting is particularly crucial for locally deployed, smaller-parameter models. Max tokens value can be calculated by this formula:
>  `LLM_TIMEOUT * llm_output_tokens/second`  (i.e. `9000 = 180s * 50 tokens/s`)

## What's New

* refact: Enhance KG Extraction with Improved Prompts and Parser Robustness by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2032
* feat: Limit Pipeline Status History Messages to Latest 1000 Entries by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2064
* feature: Enhance document status display with metadata tooltips and better icons by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2070
* refactor: Optimize Entity Extraction for Small Parameter LLMs with Enhanced Prompt Caching by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2076 https://github.com/HKUDS/LightRAG/pull/2072
* Feature: Add LLM COT Rendering support for WebUI by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2077
* feat: Add Deepseek Sytle CoT Support for Open AI Compatible LLM Provider by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2086
* Add `query_data` function and  /query/data API endpoint to LightRag for retrieval structured response by @tongda in https://github.com/HKUDS/LightRAG/pull/2036 https://github.com/HKUDS/LightRAG/pull/2100

## What's Fixed

* Fix: Eliminate Lambda Closure Bug in Embedding Function Creation by @avchauzov in https://github.com/HKUDS/LightRAG/pull/2028
* refac: Eliminate Conditional Imports and Simplify Initialization by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2029
* Fix: Preserve Leading Spaces in Graph Label Selection by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2030
* Fix ENTITY_TYPES Environment Variable Handling by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2034
* refac: Enhanced Entity Relation Extraction Text Sanitization and Normalization by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2031
* Fix LLM output instability for <|> tuple delimiter by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2035
* Enhance KG Extraction for LLM with Small Parameters by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2051
* Add VDB error handling with retries for data consistency by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2055
* Fix incorrect variable name in NetworkXStorage file path by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2060
* refact: Smart Configuration Caching and Conditional Logging by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2068
* refactor: Improved Exception Handling with Context-Aware Error Messages by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2069
* fix env file example by @k-shlomi in https://github.com/HKUDS/LightRAG/pull/2075
* Increase default Gunicorn worker timeout from 210 to 300 seconds by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2078
* Fix assistant message display with content fallback by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2079
* Prompt Optimization: remove angle brackets from entity and relationship output formats by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2082
* Refactor PostgreSQL Graph Query by Native SQL and Standardized Parameter Passing by @Matt23-star in https://github.com/HKUDS/LightRAG/pull/2027
* Update env.example by @rolotumazi in https://github.com/HKUDS/LightRAG/pull/2091
* refactor: Optimize Prompt and Fault Tolerance for LLM with Smaller Param LLM by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2093

## New Contributors

* @avchauzov made their first contribution in https://github.com/HKUDS/LightRAG/pull/2028
* @k-shlomi made their first contribution in https://github.com/HKUDS/LightRAG/pull/2075
* @rolotumazi made their first contribution in https://github.com/HKUDS/LightRAG/pull/2091
* @tongda made their first contribution in https://github.com/HKUDS/LightRAG/pull/2036

**Full Changelog**: https://github.com/HKUDS/LightRAG/compare/v1.4.7...v1.4.8