Update app.py
Browse files
app.py
CHANGED
|
@@ -72,6 +72,8 @@ else:
|
|
| 72 |
#print(response.choices[0].message.content)
|
| 73 |
|
| 74 |
|
|
|
|
|
|
|
| 75 |
|
| 76 |
embedding_model = SentenceTransformerEmbeddings(model_name='thenlper/gte-large')
|
| 77 |
# Define the embedding model and the vectorstore
|
|
@@ -94,6 +96,7 @@ retriever = vectorstore_persisted.as_retriever(
|
|
| 94 |
|
| 95 |
results = vectorstore_persisted.similarity_search("AI governance", k=5)
|
| 96 |
|
|
|
|
| 97 |
print(f"Retrieved {len(results)} results")
|
| 98 |
for doc in results:
|
| 99 |
print("Doc:", doc.page_content[:200])
|
|
|
|
| 72 |
#print(response.choices[0].message.content)
|
| 73 |
|
| 74 |
|
| 75 |
+
client = PersistentClient(path="./report_10kdb")
|
| 76 |
+
print("Available collections:", client.list_collections())
|
| 77 |
|
| 78 |
embedding_model = SentenceTransformerEmbeddings(model_name='thenlper/gte-large')
|
| 79 |
# Define the embedding model and the vectorstore
|
|
|
|
| 96 |
|
| 97 |
results = vectorstore_persisted.similarity_search("AI governance", k=5)
|
| 98 |
|
| 99 |
+
|
| 100 |
print(f"Retrieved {len(results)} results")
|
| 101 |
for doc in results:
|
| 102 |
print("Doc:", doc.page_content[:200])
|