gmakstutis/ragflow
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

refine context length (#1813)

Browse source 
### What problem does this PR solve?

#1594
### Type of change

- [x] Performance Improvement
This commit is contained in:
Kevin Hu 2024-08-05 18:22:01 +08:00 • committed by GitHub
parent 5b013da4d6
commit 5650442b0b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
graphrag/index.py
View file

@ -68,7 +68,7 @@ def build_knowlege_graph_chunks(tenant_id: str, chunks: List[str], callback, ent
llm_bdl = LLMBundle(tenant_id, LLMType.CHAT) llm_bdl = LLMBundle(tenant_id, LLMType.CHAT)
ext = GraphExtractor(llm_bdl) ext = GraphExtractor(llm_bdl)
left_token_count = llm_bdl.max_length - ext.prompt_token_count - 1024 left_token_count = llm_bdl.max_length - ext.prompt_token_count - 1024
left_token_count = llm_bdl.max_length * 0.4 left_token_count = max(llm_bdl.max_length * 0.8, left_token_count)
assert left_token_count > 0, f"The LLM context length({llm_bdl.max_length}) is smaller than prompt({ext.prompt_token_count})" assert left_token_count > 0, f"The LLM context length({llm_bdl.max_length}) is smaller than prompt({ext.prompt_token_count})"