fix wechat
This commit is contained in:
@@ -192,7 +192,7 @@ All RAG examples share these common parameters. **Interactive mode** is availabl
|
|||||||
|
|
||||||
# Search Parameters
|
# Search Parameters
|
||||||
--top-k N # Number of results to retrieve (default: 20)
|
--top-k N # Number of results to retrieve (default: 20)
|
||||||
--search-complexity N # Search complexity for graph traversal (default: 64)
|
--search-complexity N # Search complexity for graph traversal (default: 32)
|
||||||
|
|
||||||
# Chunking Parameters
|
# Chunking Parameters
|
||||||
--chunk-size N # Size of text chunks (default varies by source: 256 for most, 192 for WeChat)
|
--chunk-size N # Size of text chunks (default varies by source: 256 for most, 192 for WeChat)
|
||||||
|
|||||||
@@ -18,6 +18,7 @@ class EmailRAG(BaseRAGExample):
|
|||||||
|
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
# Set default values BEFORE calling super().__init__
|
# Set default values BEFORE calling super().__init__
|
||||||
|
self.max_items_default = -1 # Process all emails by default
|
||||||
self.embedding_model_default = (
|
self.embedding_model_default = (
|
||||||
"sentence-transformers/all-MiniLM-L6-v2" # Fast 384-dim model
|
"sentence-transformers/all-MiniLM-L6-v2" # Fast 384-dim model
|
||||||
)
|
)
|
||||||
|
|||||||
@@ -19,7 +19,7 @@ class WeChatRAG(BaseRAGExample):
|
|||||||
|
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
# Set default values BEFORE calling super().__init__
|
# Set default values BEFORE calling super().__init__
|
||||||
self.max_items_default = 50 # Match original default
|
self.max_items_default = -1 # Match original default
|
||||||
self.embedding_model_default = (
|
self.embedding_model_default = (
|
||||||
"sentence-transformers/all-MiniLM-L6-v2" # Fast 384-dim model
|
"sentence-transformers/all-MiniLM-L6-v2" # Fast 384-dim model
|
||||||
)
|
)
|
||||||
@@ -143,6 +143,7 @@ class WeChatRAG(BaseRAGExample):
|
|||||||
return []
|
return []
|
||||||
|
|
||||||
print(f"\nTotal loaded {len(all_documents)} chat documents from {len(export_dirs)} exports")
|
print(f"\nTotal loaded {len(all_documents)} chat documents from {len(export_dirs)} exports")
|
||||||
|
print("now starting to split into text chunks ... take some time")
|
||||||
|
|
||||||
# Convert to text chunks with contact information
|
# Convert to text chunks with contact information
|
||||||
all_texts = []
|
all_texts = []
|
||||||
|
|||||||
@@ -463,8 +463,9 @@ class LeannSearcher:
|
|||||||
print(
|
print(
|
||||||
f"Leann metadata file not found at {self.meta_path_str}, and you may need to rm -rf {parent_dir}"
|
f"Leann metadata file not found at {self.meta_path_str}, and you may need to rm -rf {parent_dir}"
|
||||||
)
|
)
|
||||||
|
# highlight in red the filenotfound error
|
||||||
raise FileNotFoundError(
|
raise FileNotFoundError(
|
||||||
f"Leann metadata file not found at {self.meta_path_str}, you may need to rm -rf {parent_dir}"
|
f"Leann metadata file not found at {self.meta_path_str}, \033[91m you may need to rm -rf {parent_dir}\033[0m"
|
||||||
)
|
)
|
||||||
with open(self.meta_path_str, encoding="utf-8") as f:
|
with open(self.meta_path_str, encoding="utf-8") as f:
|
||||||
self.meta_data = json.load(f)
|
self.meta_data = json.load(f)
|
||||||
|
|||||||
Reference in New Issue
Block a user