LightRAG/lightrag
yangdx b03bb48e24 feat: Refine summary logic and add dedicated Ollama num_ctx config
- Refactor the trigger condition for LLM-based summarization of entities and relations. Instead of relying on character length, the summary is now triggered when the number of merged description fragments exceeds a configured threshold. This provides a more robust and logical condition for consolidation.
- Introduce the `OLLAMA_NUM_CTX` environment variable to explicitly configure the context window size (`num_ctx`) for Ollama models. This decouples the model's context length from the `MAX_TOKENS` parameter, which is now specifically used to limit input for summary generation, making the configuration clearer and more flexible.
- Updated `README` files, `env.example`, and default values to reflect these changes.
2025-07-14 01:55:04 +08:00
..
api feat: Refine summary logic and add dedicated Ollama num_ctx config 2025-07-14 01:55:04 +08:00
kg Increase field lengths for entity and file paths for PostgreSQL 2025-07-14 00:24:54 +08:00
llm Fix linting 2025-07-08 18:17:21 +08:00
tools
__init__.py Bump core version to 1.4.0 2025-07-09 04:43:20 +08:00
base.py update chunks truncation method 2025-07-08 13:31:05 +08:00
constants.py Add max_gleaning to env 2025-07-01 17:13:33 +08:00
exceptions.py
lightrag.py feat: Refine summary logic and add dedicated Ollama num_ctx config 2025-07-14 01:55:04 +08:00
llm.py
namespace.py Remove namespace_prefix 2025-07-06 00:16:47 +08:00
operate.py feat: Refine summary logic and add dedicated Ollama num_ctx config 2025-07-14 01:55:04 +08:00
prompt.py feat: Optimize document deletion performance 2025-06-25 12:37:57 +08:00
rerank.py Simplify Configuration 2025-07-08 11:16:34 +08:00
types.py Add is_truncated to graph query for NetworkX graph db 2025-04-02 22:12:20 +08:00
utils.py remove <think> tag for entities and keywords extraction 2025-07-08 14:59:15 +08:00
utils_graph.py Fix GRAPH_FIELD_SEP import typo 2025-06-29 01:28:39 +05:00