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

Linting and formatting

Browse Source
This commit is contained in:
Pankaj Kaushal
2025-02-19 15:01:51 +01:00
parent 04604841c9
commit 277070e03b
2 changed files with 46 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
examples/lightrag_api_llamaindex_direct_demo_simplified.py
View File

@@ -1,6 +1,9 @@
import os import os
from lightrag import LightRAG, QueryParam from lightrag import LightRAG, QueryParam
from lightrag.wrapper.llama_index_impl import llama_index_complete_if_cache, llama_index_embed from lightrag.wrapper.llama_index_impl import (
llama_index_complete_if_cache,
llama_index_embed,
)
from lightrag.utils import EmbeddingFunc from lightrag.utils import EmbeddingFunc
from llama_index.llms.openai import OpenAI from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding from llama_index.embeddings.openai import OpenAIEmbedding
@@ -25,20 +28,21 @@ OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "your-api-key-here")
if not os.path.exists(WORKING_DIR): if not os.path.exists(WORKING_DIR):
os.mkdir(WORKING_DIR) os.mkdir(WORKING_DIR)
# Initialize LLM function # Initialize LLM function
async def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwargs): async def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwargs):
try: try:
# Initialize OpenAI if not in kwargs # Initialize OpenAI if not in kwargs
if 'llm_instance' not in kwargs: if "llm_instance" not in kwargs:
llm_instance = OpenAI( llm_instance = OpenAI(
model=LLM_MODEL, model=LLM_MODEL,
api_key=OPENAI_API_KEY, api_key=OPENAI_API_KEY,
temperature=0.7, temperature=0.7,
) )
kwargs['llm_instance'] = llm_instance kwargs["llm_instance"] = llm_instance
response = await llama_index_complete_if_cache( response = await llama_index_complete_if_cache(
kwargs['llm_instance'], kwargs["llm_instance"],
prompt, prompt,
system_prompt=system_prompt, system_prompt=system_prompt,
history_messages=history_messages, history_messages=history_messages,
@@ -49,6 +53,7 @@ async def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwar
print(f"LLM request failed: {str(e)}") print(f"LLM request failed: {str(e)}")
raise raise
# Initialize embedding function # Initialize embedding function
async def embedding_func(texts): async def embedding_func(texts):
try: try:
@@ -61,6 +66,7 @@ async def embedding_func(texts):
print(f"Embedding failed: {str(e)}") print(f"Embedding failed: {str(e)}")
raise raise
# Get embedding dimension # Get embedding dimension
async def get_embedding_dim(): async def get_embedding_dim():
test_text = ["This is a test sentence."] test_text = ["This is a test sentence."]
@@ -69,6 +75,7 @@ async def get_embedding_dim():
print(f"embedding_dim={embedding_dim}") print(f"embedding_dim={embedding_dim}")
return embedding_dim return embedding_dim
# Initialize RAG instance # Initialize RAG instance
rag = LightRAG( rag = LightRAG(
working_dir=WORKING_DIR, working_dir=WORKING_DIR,
@@ -86,13 +93,21 @@ with open("./book.txt", "r", encoding="utf-8") as f:
# Test different query modes # Test different query modes
print("\nNaive Search:") print("\nNaive Search:")
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="naive"))) print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="naive"))
)
print("\nLocal Search:") print("\nLocal Search:")
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="local"))) print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="local"))
)
print("\nGlobal Search:") print("\nGlobal Search:")
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="global"))) print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="global"))
)
print("\nHybrid Search:") print("\nHybrid Search:")
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid"))) print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid"))
)

31
examples/lightrag_api_llamaindex_litellm_demo_simplified.py
View File

@@ -1,6 +1,9 @@
import os import os
from lightrag import LightRAG, QueryParam from lightrag import LightRAG, QueryParam
from lightrag.wrapper.llama_index_impl import llama_index_complete_if_cache, llama_index_embed from lightrag.wrapper.llama_index_impl import (
llama_index_complete_if_cache,
llama_index_embed,
)
from lightrag.utils import EmbeddingFunc from lightrag.utils import EmbeddingFunc
from llama_index.llms.litellm import LiteLLM from llama_index.llms.litellm import LiteLLM
from llama_index.embeddings.litellm import LiteLLMEmbedding from llama_index.embeddings.litellm import LiteLLMEmbedding
@@ -27,21 +30,22 @@ LITELLM_KEY = os.environ.get("LITELLM_KEY", "sk-1234")
if not os.path.exists(WORKING_DIR): if not os.path.exists(WORKING_DIR):
os.mkdir(WORKING_DIR) os.mkdir(WORKING_DIR)
# Initialize LLM function # Initialize LLM function
async def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwargs): async def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwargs):
try: try:
# Initialize LiteLLM if not in kwargs # Initialize LiteLLM if not in kwargs
if 'llm_instance' not in kwargs: if "llm_instance" not in kwargs:
llm_instance = LiteLLM( llm_instance = LiteLLM(
model=f"openai/{LLM_MODEL}", # Format: "provider/model_name" model=f"openai/{LLM_MODEL}", # Format: "provider/model_name"
api_base=LITELLM_URL, api_base=LITELLM_URL,
api_key=LITELLM_KEY, api_key=LITELLM_KEY,
temperature=0.7, temperature=0.7,
) )
kwargs['llm_instance'] = llm_instance kwargs["llm_instance"] = llm_instance
response = await llama_index_complete_if_cache( response = await llama_index_complete_if_cache(
kwargs['llm_instance'], kwargs["llm_instance"],
prompt, prompt,
system_prompt=system_prompt, system_prompt=system_prompt,
history_messages=history_messages, history_messages=history_messages,
@@ -52,6 +56,7 @@ async def llm_model_func(prompt, system_prompt=None, history_messages=[], **kwar
print(f"LLM request failed: {str(e)}") print(f"LLM request failed: {str(e)}")
raise raise
# Initialize embedding function # Initialize embedding function
async def embedding_func(texts): async def embedding_func(texts):
try: try:
@@ -65,6 +70,7 @@ async def embedding_func(texts):
print(f"Embedding failed: {str(e)}") print(f"Embedding failed: {str(e)}")
raise raise
# Get embedding dimension # Get embedding dimension
async def get_embedding_dim(): async def get_embedding_dim():
test_text = ["This is a test sentence."] test_text = ["This is a test sentence."]
@@ -73,6 +79,7 @@ async def get_embedding_dim():
print(f"embedding_dim={embedding_dim}") print(f"embedding_dim={embedding_dim}")
return embedding_dim return embedding_dim
# Initialize RAG instance # Initialize RAG instance
rag = LightRAG( rag = LightRAG(
working_dir=WORKING_DIR, working_dir=WORKING_DIR,
@@ -90,13 +97,21 @@ with open("./book.txt", "r", encoding="utf-8") as f:
# Test different query modes # Test different query modes
print("\nNaive Search:") print("\nNaive Search:")
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="naive"))) print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="naive"))
)
print("\nLocal Search:") print("\nLocal Search:")
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="local"))) print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="local"))
)
print("\nGlobal Search:") print("\nGlobal Search:")
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="global"))) print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="global"))
)
print("\nHybrid Search:") print("\nHybrid Search:")
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid"))) print(
rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid"))
)