v1.4.7

## Important Notes

* **Doc-id based chunk filtering feature is remove  from PostgreSQL vector storage**.
* **Prompt template has been updated, invalidating all LLM caches**
* **The default value of the FORCE_LLM_SUMMARY_ON_MERGE environment variable has been changed from 4 to 8**. This adjustment significantly reduces the number of LLM calls during the documentation indexing phase, thereby shortening the overall document processing time.
* **Added support for multiple Rerank Providers (Cohere AI, Jina AI, Aliyun Dashscope)**. If Rerank was previously enabled, and new env var must be set to enable rerank again: 

```
RERANK_BINDING=cohere
```

* **Introduced a new environment variable, LLM_TIMEOUT, to specifically control the Large Language Model (LLM) timeout**. The existing TIMEOUT variable now exclusively manages the Gunicorn worker timeout. The default LLM timeout is set to 180 seconds. If you previously relied on the TIMEOUT variable for LLM timeout configuration, please update your settings to use LLM_TIMEOUT instead:

```
LLM_TIMEOUT=180
```

* **Add comprehensive environment variable settings for OpenAI and Ollama Large Language Model (LLM) Bindings**.
The generic TEMPERATURE environment variable for LLM temperature control has been deprecated. Instead, LLM temperature is now configured using binding-specific environment variables: 

```
# Temperature setting for OpenAI binding
OPENAI_LLM_TEMPERATURE=0.8

# Temperature setting for Ollama binding
OLLAMA_LLM_TEMPERATURE=1.0
```

To mitigate endless output loops and prevent greedy decoding for Qwen3, set the temperature parameter to a value between 0.8 and 1.0.  To disable the model's "Thinking" mode, please refer to the following configuration:

```
### Qwen3 Specific Parameters depoly by vLLM
# OPENAI_LLM_EXTRA_BODY='{"chat_template_kwargs": {"enable_thinking": false}}'

### OpenRouter Specific Parameters
# OPENAI_LLM_EXTRA_BODY='{"reasoning": {"enabled": false}}'
```

For a full list of support options, use the following command:

```
lightrag-server --llm-binding openai --help
lightrag-server --llm-binding ollama --help
lightrag-server --embedding-binding ollama --help
```

* **A Full list of new env vars added or new default values**:

```
# Timeout for LLM requests (seconds)
LLM_TIMEOUT=180

# Timeout for embedding requests (seconds)
EMBEDDING_TIMEOUT=30

### Number of summary segments or tokens to trigger LLM summary on entity/relation merge (at least 3 is recommended)
FORCE_LLM_SUMMARY_ON_MERGE=8

### Max description token size to trigger LLM summary
SUMMARY_MAX_TOKENS = 1200

### Recommended LLM summary output length in tokens
SUMMARY_LENGTH_RECOMMENDED=600

### Maximum context size sent to LLM for description summary
SUMMARY_CONTEXT_SIZE=12000

### RERANK_BINDING type:  null, cohere, jina, aliyun
RERANK_BINDING=null

### Enable rerank by default in query params when RERANK_BINDING is not null
# RERANK_BY_DEFAULT=True

### chunk selection strategies
###     VECTOR: Pick KG chunks by vector similarity, delivered chunks to the LLM aligning more closely with naive retrieval
###     WEIGHT: Pick KG chunks by entity and chunk weight, delivered more solely KG related chunks to the LLM
###     If reranking is enabled, the impact of chunk selection strategies will be diminished.
KG_CHUNK_PICK_METHOD=VECTOR

### Entity types that the LLM will attempt to recognize
ENTITY_TYPES=["person", "organization", "location", "event", "concept"]
```

## What's News

* feat: **Add OpenAI LLM Options Support** by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1910
* feat: add tiktoken cache directory support for offline deployment by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1914
* Refact：Enhanced Neo4j Connection Lifecycle Management by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1924
* Add Vector Index Support for PostgreSQL KG by @Matt23-star in https://github.com/HKUDS/LightRAG/pull/1922
* Add AWS Bedrock LLm Binding Support #1733 by @sjjpo2002 in https://github.com/HKUDS/LightRAG/pull/1948
* Feat: Reprocessing of failed documents without the original file being present by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1954
* Feat: add KG related chunks selection by vector similarity by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1959
* Feat: Optimize error handling for document processing pipeline by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1965
* Add Chinese pinyin sorting support across document operations by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1967
* Refactor: Remove file_path and created_at from entity and relation query context send to LLM by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1976
* Refactor Postgres Batch Queries for Scalability, Safety, and Vector Search Optimization by @Matt23-star in https://github.com/HKUDS/LightRAG/pull/1964
* feat: Support turning off thinking on OpenRouter/vLLM by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1987
* feat: **Add Multiple Rerank Provider Support** by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1993
* feat: Add clear error messages for uninitialized storage by @albertgilopez in https://github.com/HKUDS/LightRAG/pull/1978
* feat: Add diagnostic tool to check initialization status by @albertgilopez in https://github.com/HKUDS/LightRAG/pull/1979
* feat: Improve Empty Keyword Handling logic by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1996
* refac: Refactor LLM Summary Generation Algorithm by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2006
* Added entity_types as a user defined variable (via .env) by @thiborose in https://github.com/HKUDS/LightRAG/pull/1998
* refac: Enhanced Timeout Handling for LLM Priority Queue by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2024
* refac: Remove deprecated doc-id based filtering from vector storage queries by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2025

## What''s Fixed

* Fix ollama stop option handling and enhance temperature configuration by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1909
* Feat: Change embedding formats from float to base64 for efficiency by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1913
* Refact: Optimized LLM Cache Hash Key Generation by Including All Query Parameters by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1915
* Fix: Unify  document chunks context format in only_need_context query by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1923
* Fix: Update OpenAI embedding handling for both list and base64 embeddings by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1928
* Fix: Initialize first_stage_tasks and entity_relation_task to prevent empty-task cancel errors by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1931
* Fix: **Resolve workspace isolation issues across multiple storage** implementations by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1941
* Fix: remove query params from cache key generation for keyword extraction by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1949
* Refac: uniformly protected with the get_data_init_lock for all storage initializations by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1951
* Fixes crash when processing files with UTF-8 encoding error by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1952
* Fix Document Selection Issues After Pagination Implementation by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1966
* Change the status from PROCESSING/FAILED to PENDING at the beginning of document processing pipeline by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1971
* Refac: Increase file_path field length to 32768 and add schema migration for Milvus DB by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1975
* Optimize keyword extraction prompt, and remove conversation history from keyword extraction by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1977
* Fix(UI): Implement XLSX format upload support for web UI by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1982
* Fix: resolved UTF-8 encoding error during document processing by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1983
* Fix: Preserve Document List Pagination During Pipeline Status Changes by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/1992
* Update README-zh.md by @OnesoftQwQ in https://github.com/HKUDS/LightRAG/pull/1989
* Fi: Added import of OpenAILLMOptions when using azure_openai by @thiborose in https://github.com/HKUDS/LightRAG/pull/1999
* fix(webui): resolve document status grouping issue in DocumentManager by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2013
* fix mismatch of 'error' and 'error_msg' in MongoDB by @LinkinPony in https://github.com/HKUDS/LightRAG/pull/2009
* Fix UTF-8 Encoding Issues Causing Document Processing Failures by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2017
* docs(config): fix typo in .env comments by @SandmeyerX in https://github.com/HKUDS/LightRAG/pull/2021
* fix: adjust the EMBEDDING_BINDING_HOST for openai in the env.example by @pedrofs in https://github.com/HKUDS/LightRAG/pull/2026

## New Contributors

* @Matt23-star made their first contribution in https://github.com/HKUDS/LightRAG/pull/1922
* @sjjpo2002 made their first contribution in https://github.com/HKUDS/LightRAG/pull/1948
* @OnesoftQwQ made their first contribution in https://github.com/HKUDS/LightRAG/pull/1989
* @albertgilopez made their first contribution in https://github.com/HKUDS/LightRAG/pull/1978
* @thiborose made their first contribution in https://github.com/HKUDS/LightRAG/pull/1999
* @LinkinPony made their first contribution in https://github.com/HKUDS/LightRAG/pull/2009
* @SandmeyerX made their first contribution in https://github.com/HKUDS/LightRAG/pull/2021
* @pedrofs made their first contribution in https://github.com/HKUDS/LightRAG/pull/2026

**Full Changelog**: https://github.com/HKUDS/LightRAG/compare/v1.4.6...v1.4.7