root/Gitcloned-RAG-Anything
1
1
Fork 0
Code Issues Pull Requests Projects Releases Activity

chores: refactor examples

Browse Source
This commit is contained in:
laansdole
2025-10-04 21:27:41 +07:00
parent 0f6d3ea83a
commit ab552321ae
3 changed files with 20 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/insert_content_list_example.py
View File

@@ -245,13 +245,16 @@ async def demo_insert_content_list(
else:
return llm_model_func(prompt, system_prompt, history_messages, **kwargs)
# Define embedding function
# Define embedding function - using environment variables for configuration
embedding_dim = int(os.getenv("EMBEDDING_DIM", "3072"))
embedding_model = os.getenv("EMBEDDING_MODEL", "text-embedding-3-large")
embedding_func = EmbeddingFunc(
embedding_dim=3072,
embedding_dim=embedding_dim,
max_token_size=8192,
func=lambda texts: openai_embed(
texts,
model="text-embedding-3-large",
model=embedding_model,
api_key=api_key,
base_url=base_url,
),

10
examples/modalprocessors_example.py
View File

@@ -164,14 +164,20 @@ async def process_equation_example(lightrag: LightRAG, llm_model_func):
async def initialize_rag(api_key: str, base_url: str = None):
# Use environment variables for embedding configuration
import os
embedding_dim = int(os.getenv("EMBEDDING_DIM", "3072"))
embedding_model = os.getenv("EMBEDDING_MODEL", "text-embedding-3-large")
rag = LightRAG(
working_dir=WORKING_DIR,
embedding_func=EmbeddingFunc(
embedding_dim=3072,
embedding_dim=embedding_dim,
max_token_size=8192,
func=lambda texts: openai_embed(
texts,
model="text-embedding-3-large",
model=embedding_model,
api_key=api_key,
base_url=base_url,
),

9
examples/raganything_example.py
View File

@@ -182,13 +182,16 @@ async def process_with_rag(
else:
return llm_model_func(prompt, system_prompt, history_messages, **kwargs)
# Define embedding function
# Define embedding function - using environment variables for configuration
embedding_dim = int(os.getenv("EMBEDDING_DIM", "3072"))
embedding_model = os.getenv("EMBEDDING_MODEL", "text-embedding-3-large")
embedding_func = EmbeddingFunc(
embedding_dim=3072,
embedding_dim=embedding_dim,
max_token_size=8192,
func=lambda texts: openai_embed(
texts,
model="text-embedding-3-large",
model=embedding_model,
api_key=api_key,
base_url=base_url,
),