Merge pull request #406 from magicyuan876/main

添加查询时使用embedding缓存功能

README.md

@@ -596,6 +596,7 @@ if __name__ == "__main__":
 | **enable\_llm\_cache** | `bool` | If `TRUE`, stores LLM results in cache; repeated prompts return cached responses | `TRUE` |
 | **addon\_params** | `dict` | Additional parameters, e.g., `{"example_number": 1, "language": "Simplified Chinese"}`: sets example limit and output language | `example_number: all examples, language: English` |
 | **convert\_response\_to\_json\_func** | `callable` | Not used | `convert_response_to_json` |
+| **embedding\_cache\_config** | `dict` | Configuration for embedding cache. Includes `enabled` (bool) to toggle cache and `similarity_threshold` (float) for cache retrieval | `{"enabled": False, "similarity_threshold": 0.95}` |
 
 ## API Server Implementation
 

examples/lightrag_openai_compatible_demo_embedding_cache.py

@@ -0,0 +1,112 @@
+import os
+import asyncio
+from lightrag import LightRAG, QueryParam
+from lightrag.llm import openai_complete_if_cache, openai_embedding
+from lightrag.utils import EmbeddingFunc
+import numpy as np
+
+WORKING_DIR = "./dickens"
+
+if not os.path.exists(WORKING_DIR):
+    os.mkdir(WORKING_DIR)
+
+
+async def llm_model_func(
+    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
+) -> str:
+    return await openai_complete_if_cache(
+        "solar-mini",
+        prompt,
+        system_prompt=system_prompt,
+        history_messages=history_messages,
+        api_key=os.getenv("UPSTAGE_API_KEY"),
+        base_url="https://api.upstage.ai/v1/solar",
+        **kwargs,
+    )
+
+
+async def embedding_func(texts: list[str]) -> np.ndarray:
+    return await openai_embedding(
+        texts,
+        model="solar-embedding-1-large-query",
+        api_key=os.getenv("UPSTAGE_API_KEY"),
+        base_url="https://api.upstage.ai/v1/solar",
+    )
+
+
+async def get_embedding_dim():
+    test_text = ["This is a test sentence."]
+    embedding = await embedding_func(test_text)
+    embedding_dim = embedding.shape[1]
+    return embedding_dim
+
+
+# function test
+async def test_funcs():
+    result = await llm_model_func("How are you?")
+    print("llm_model_func: ", result)
+
+    result = await embedding_func(["How are you?"])
+    print("embedding_func: ", result)
+
+
+# asyncio.run(test_funcs())
+
+
+async def main():
+    try:
+        embedding_dimension = await get_embedding_dim()
+        print(f"Detected embedding dimension: {embedding_dimension}")
+
+        rag = LightRAG(
+            working_dir=WORKING_DIR,
+            embedding_cache_config={
+                "enabled": True,
+                "similarity_threshold": 0.90,
+            },
+            llm_model_func=llm_model_func,
+            embedding_func=EmbeddingFunc(
+                embedding_dim=embedding_dimension,
+                max_token_size=8192,
+                func=embedding_func,
+            ),
+        )
+
+        with open("./book.txt", "r", encoding="utf-8") as f:
+            await rag.ainsert(f.read())
+
+        # Perform naive search
+        print(
+            await rag.aquery(
+                "What are the top themes in this story?", param=QueryParam(mode="naive")
+            )
+        )
+
+        # Perform local search
+        print(
+            await rag.aquery(
+                "What are the top themes in this story?", param=QueryParam(mode="local")
+            )
+        )
+
+        # Perform global search
+        print(
+            await rag.aquery(
+                "What are the top themes in this story?",
+                param=QueryParam(mode="global"),
+            )
+        )
+
+        # Perform hybrid search
+        print(
+            await rag.aquery(
+                "What are the top themes in this story?",
+                param=QueryParam(mode="hybrid"),
+            )
+        )
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

lightrag/lightrag.py

@@ -85,7 +85,10 @@ class LightRAG:
     working_dir: str = field(
         default_factory=lambda: f"./lightrag_cache_{datetime.now().strftime('%Y-%m-%d-%H:%M:%S')}"
     )
-
+    # Default not to use embedding cache
+    embedding_cache_config: dict = field(
+        default_factory=lambda: {"enabled": False, "similarity_threshold": 0.95}
+    )
     kv_storage: str = field(default="JsonKVStorage")
     vector_storage: str = field(default="NanoVectorDBStorage")
     graph_storage: str = field(default="NetworkXStorage")