Update app.py
Browse files
app.py
CHANGED
|
@@ -44,14 +44,26 @@ def get_csv_file(csv_docs):
|
|
| 44 |
return csv_doc # μΆμΆν ν
μ€νΈλ₯Ό λ°νν©λλ€.
|
| 45 |
|
| 46 |
def get_json_file(json_docs):
|
|
|
|
| 47 |
try:
|
| 48 |
temp_dir = tempfile.TemporaryDirectory() # μμ λλ ν 리λ₯Ό μμ±ν©λλ€.
|
| 49 |
temp_filepath = os.path.join(temp_dir.name, "temp_file.json") # μμ νμΌ κ²½λ‘λ₯Ό μμ±ν©λλ€.
|
| 50 |
with open(temp_filepath, "wb") as f:
|
| 51 |
f.write(json_docs.getvalue()) # JSON λ¬Έμμ λ΄μ©μ μμ νμΌμ μλλ€.
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
except Exception as e:
|
| 56 |
st.error(f"Error loading JSON file: {e}")
|
| 57 |
return []
|
|
@@ -59,6 +71,7 @@ def get_json_file(json_docs):
|
|
| 59 |
|
| 60 |
|
| 61 |
|
|
|
|
| 62 |
# λ¬Έμλ€μ μ²λ¦¬νμ¬ ν
μ€νΈ μ²ν¬λ‘ λλλ ν¨μμ
λλ€.
|
| 63 |
def get_text_chunks(documents):
|
| 64 |
text_splitter = RecursiveCharacterTextSplitter(
|
|
|
|
| 44 |
return csv_doc # μΆμΆν ν
μ€νΈλ₯Ό λ°νν©λλ€.
|
| 45 |
|
| 46 |
def get_json_file(json_docs):
|
| 47 |
+
def get_json_file(json_docs):
|
| 48 |
try:
|
| 49 |
temp_dir = tempfile.TemporaryDirectory() # μμ λλ ν 리λ₯Ό μμ±ν©λλ€.
|
| 50 |
temp_filepath = os.path.join(temp_dir.name, "temp_file.json") # μμ νμΌ κ²½λ‘λ₯Ό μμ±ν©λλ€.
|
| 51 |
with open(temp_filepath, "wb") as f:
|
| 52 |
f.write(json_docs.getvalue()) # JSON λ¬Έμμ λ΄μ©μ μμ νμΌμ μλλ€.
|
| 53 |
+
|
| 54 |
+
# Load JSON file
|
| 55 |
+
json_loader = JSONLoader(temp_filepath, jq_schema='.messages[].content', text_content=False)
|
| 56 |
+
json_doc = json_loader.load()
|
| 57 |
+
|
| 58 |
+
# Remove empty chunks
|
| 59 |
+
non_empty_chunks = [chunk for chunk in json_doc if len(chunk) > 0]
|
| 60 |
+
|
| 61 |
+
# Check if any non-empty chunks are present
|
| 62 |
+
if not non_empty_chunks:
|
| 63 |
+
st.error("No non-empty chunks found in the JSON file.")
|
| 64 |
+
return []
|
| 65 |
+
|
| 66 |
+
return non_empty_chunks
|
| 67 |
except Exception as e:
|
| 68 |
st.error(f"Error loading JSON file: {e}")
|
| 69 |
return []
|
|
|
|
| 71 |
|
| 72 |
|
| 73 |
|
| 74 |
+
|
| 75 |
# λ¬Έμλ€μ μ²λ¦¬νμ¬ ν
μ€νΈ μ²ν¬λ‘ λλλ ν¨μμ
λλ€.
|
| 76 |
def get_text_chunks(documents):
|
| 77 |
text_splitter = RecursiveCharacterTextSplitter(
|