Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -17,7 +17,6 @@ RETRIEVER_URL = os.getenv("RETRIEVER_URL")
|
|
| 17 |
RANKER_URL = os.getenv("RANKER_URL")
|
| 18 |
HF_TOKEN = os.getenv("HF_TOKEN")
|
| 19 |
|
| 20 |
-
|
| 21 |
class Retriever(EmbeddingRetriever):
|
| 22 |
def __init__(
|
| 23 |
self,
|
|
@@ -120,17 +119,28 @@ EXAMPLES = [
|
|
| 120 |
"The Sphinx is in Egypt.",
|
| 121 |
]
|
| 122 |
|
| 123 |
-
if os.path.exists("faiss_document_store.db"):
|
| 124 |
-
|
| 125 |
-
|
| 126 |
-
document_store
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
|
| 132 |
-
retriever = Retriever(document_store=document_store, top_k=TOP_K, batch_size=BATCH_SIZE)
|
| 133 |
-
document_store.update_embeddings(retriever=retriever)
|
| 134 |
ranker = Ranker()
|
| 135 |
|
| 136 |
pipe = Pipeline()
|
|
@@ -142,12 +152,12 @@ def run(query: str) -> dict:
|
|
| 142 |
output = pipe.run(query=query)
|
| 143 |
|
| 144 |
return (
|
| 145 |
-
f"Closest document(s): {[output['documents'][i].content for i in range(TOP_K)]}"
|
| 146 |
)
|
| 147 |
|
| 148 |
|
| 149 |
-
# warm up
|
| 150 |
run("What is the capital of France?")
|
|
|
|
| 151 |
|
| 152 |
gr.Interface(
|
| 153 |
fn=run,
|
|
|
|
| 17 |
RANKER_URL = os.getenv("RANKER_URL")
|
| 18 |
HF_TOKEN = os.getenv("HF_TOKEN")
|
| 19 |
|
|
|
|
| 20 |
class Retriever(EmbeddingRetriever):
|
| 21 |
def __init__(
|
| 22 |
self,
|
|
|
|
| 119 |
"The Sphinx is in Egypt.",
|
| 120 |
]
|
| 121 |
|
| 122 |
+
if os.path.exists("faiss_document_store.db") and os.path.exists("faiss_index"):
|
| 123 |
+
document_store = FAISSDocumentStore.load("faiss_index")
|
| 124 |
+
retriever = Retriever(
|
| 125 |
+
document_store=document_store, top_k=TOP_K, batch_size=BATCH_SIZE
|
| 126 |
+
)
|
| 127 |
+
else:
|
| 128 |
+
try:
|
| 129 |
+
os.remove("faiss_index")
|
| 130 |
+
os.remove("faiss_document_store.db")
|
| 131 |
+
except FileNotFoundError:
|
| 132 |
+
pass
|
| 133 |
+
|
| 134 |
+
document_store = FAISSDocumentStore(embedding_dim=384, return_embedding=True)
|
| 135 |
+
document_store.write_documents(
|
| 136 |
+
[Document(content=d, id=i) for i, d in enumerate(EXAMPLES)]
|
| 137 |
+
)
|
| 138 |
+
retriever = Retriever(
|
| 139 |
+
document_store=document_store, top_k=TOP_K, batch_size=BATCH_SIZE
|
| 140 |
+
)
|
| 141 |
+
document_store.update_embeddings(retriever=retriever)
|
| 142 |
+
document_store.save(index_path="faiss_index")
|
| 143 |
|
|
|
|
|
|
|
| 144 |
ranker = Ranker()
|
| 145 |
|
| 146 |
pipe = Pipeline()
|
|
|
|
| 152 |
output = pipe.run(query=query)
|
| 153 |
|
| 154 |
return (
|
| 155 |
+
f"Closest ({TOP_K}) document(s): {[output['documents'][i].content for i in range(TOP_K)]}"
|
| 156 |
)
|
| 157 |
|
| 158 |
|
|
|
|
| 159 |
run("What is the capital of France?")
|
| 160 |
+
print("Warmed up successfully!")
|
| 161 |
|
| 162 |
gr.Interface(
|
| 163 |
fn=run,
|