gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

创建yangdx分支，并添加测试脚本

Browse Source
This commit is contained in:
yangdx
2025-01-14 23:04:41 +08:00
parent 61349b0fe7
commit 0bfeb237e3
2 changed files with 72 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -695,7 +695,7 @@ Output the results in the following structure:
```
</details>
### Batch Eval
### Batch Eval
To evaluate the performance of two RAG systems on high-level queries, LightRAG uses the following prompt, with the specific code available in `example/batch_eval.py`.
<details>
@@ -746,6 +746,7 @@ Output your evaluation in the following JSON format:
</details>
### Overall Performance Table
| | **Agriculture** | | **CS** | | **Legal** | | **Mix** | |
|----------------------|-------------------------|-----------------------|-----------------------|-----------------------|-----------------------|-----------------------|-----------------------|-----------------------|
| | NaiveRAG | **LightRAG** | NaiveRAG | **LightRAG** | NaiveRAG | **LightRAG** | NaiveRAG | **LightRAG** |

70
examples/lightrag_yangdx.py Normal file
View File

@@ -0,0 +1,70 @@
import asyncio
import os
import inspect
import logging
from lightrag import LightRAG, QueryParam
from lightrag.llm import ollama_model_complete, ollama_embedding
from lightrag.utils import EmbeddingFunc
WORKING_DIR = "./dickens"
logging.basicConfig(format="%(levelname)s:%(message)s", level=logging.INFO)
if not os.path.exists(WORKING_DIR):
os.mkdir(WORKING_DIR)
rag = LightRAG(
working_dir=WORKING_DIR,
llm_model_func=ollama_model_complete,
llm_model_name="gemma2:2b",
llm_model_max_async=4,
llm_model_max_token_size=32768,
llm_model_kwargs={"host": "http://localhost:11434", "options": {"num_ctx": 32768}},
embedding_func=EmbeddingFunc(
embedding_dim=768,
max_token_size=8192,
func=lambda texts: ollama_embedding(
texts, embed_model="nomic-embed-text", host="http://localhost:11434"
),
),
)
with open("./book.txt", "r", encoding="utf-8") as f:
rag.insert(f.read())
# Perform naive search
print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="naive"))
)
# Perform local search
print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="local"))
)
# Perform global search
print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="global"))
)
# Perform hybrid search
print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid"))
)
# stream response
resp = rag.query(
"What are the top themes in this story?",
param=QueryParam(mode="hybrid", stream=True),
)
async def print_stream(stream):
async for chunk in stream:
print(chunk, end="", flush=True)
if inspect.isasyncgen(resp):
asyncio.run(print_stream(resp))
else:
print(resp)