ddi-fw 0.0.125__py3-none-any.whl → 0.0.127__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- ddi_fw/langchain/storage.py +8 -6
- {ddi_fw-0.0.125.dist-info → ddi_fw-0.0.127.dist-info}/METADATA +1 -1
- {ddi_fw-0.0.125.dist-info → ddi_fw-0.0.127.dist-info}/RECORD +5 -5
- {ddi_fw-0.0.125.dist-info → ddi_fw-0.0.127.dist-info}/WHEEL +0 -0
- {ddi_fw-0.0.125.dist-info → ddi_fw-0.0.127.dist-info}/top_level.txt +0 -0
ddi_fw/langchain/storage.py
CHANGED
|
@@ -119,6 +119,7 @@ class DataFrameToVectorDB:
|
|
|
119
119
|
|
|
120
120
|
def __split_list(self, input_list, batch_size):
|
|
121
121
|
# for i in range(0, len(input_list), batch_size):
|
|
122
|
+
batch_size = len(input_list) if batch_size == None else batch_size
|
|
122
123
|
for s, e in split_dataframe_indices(input_list, batch_size):
|
|
123
124
|
yield input_list[s:e+1]
|
|
124
125
|
|
|
@@ -143,11 +144,13 @@ class DataFrameToVectorDB:
|
|
|
143
144
|
data_frame=partial_df, page_content_column=page_content_column)
|
|
144
145
|
loaded_docs = loader.load()
|
|
145
146
|
# print(loaded_docs)
|
|
146
|
-
|
|
147
|
+
documents.extend(self.__split_docs(loaded_docs))
|
|
148
|
+
split_docs_chunked = self.__split_list(
|
|
149
|
+
documents, self.batch_size)
|
|
150
|
+
for split_docs_chunk in split_docs_chunked:
|
|
151
|
+
self.vectordb.add_documents(loaded_docs)
|
|
152
|
+
self.vectordb.persist()
|
|
147
153
|
total += len(partial_df)
|
|
148
|
-
|
|
149
|
-
self.vectordb.add_documents(loaded_docs)
|
|
150
|
-
self.vectordb.persist()
|
|
151
154
|
print(f"{page_content_column}: {total}/{len(col_df)}")
|
|
152
155
|
torch.cuda.empty_cache()
|
|
153
156
|
# time.sleep(30) # The GPU will not be used during this period
|
|
@@ -253,5 +256,4 @@ def generate_embeddings(df, config_file, new_model_names, collections=None, pers
|
|
|
253
256
|
text_splitter=text_splitter,
|
|
254
257
|
batch_size=batch_size)
|
|
255
258
|
to_vector_db.store_documents(
|
|
256
|
-
|
|
257
|
-
|
|
259
|
+
df, columns, page_content_columns, partial_df_size=partial_df_size)
|
|
@@ -58,7 +58,7 @@ ddi_fw/drugbank/event_extractor.py,sha256=6odoZohhK7OdLF-LF0l-5BFq0_NMG_5jrFJbHr
|
|
|
58
58
|
ddi_fw/langchain/__init__.py,sha256=zS0CQrakWEP19biSRewFJGcBT8WBZq4899HrEKiMqUY,269
|
|
59
59
|
ddi_fw/langchain/embeddings.py,sha256=lU64a5AZ62jP8U3hTSwK0kXt7gThbwPACLfJMZ1baPA,7538
|
|
60
60
|
ddi_fw/langchain/sentence_splitter.py,sha256=h_bYElx4Ud1mwDNJfL7mUwvgadwKX3GKlSzu5L2PXzg,280
|
|
61
|
-
ddi_fw/langchain/storage.py,sha256=
|
|
61
|
+
ddi_fw/langchain/storage.py,sha256=sWeFJgCLKtMFsBev1cJ4SKy_aoG5cTx9IadY-7S99es,11101
|
|
62
62
|
ddi_fw/ml/__init__.py,sha256=tIxiW0g6q1VsmDYVXR_ovvHQR3SCir8g2bKxx_CrS7s,221
|
|
63
63
|
ddi_fw/ml/evaluation_helper.py,sha256=o4-w5Xa3t4olLW4ymx_8L-Buhe5wfQEmT2bh4Zz544c,13066
|
|
64
64
|
ddi_fw/ml/ml_helper.py,sha256=fySjIAFzkeEOvaLJhDwtCOgRhgYQ7H106eqaP16GhDY,4489
|
|
@@ -91,7 +91,7 @@ ddi_fw/utils/package_helper.py,sha256=erl8_onmhK-41zQoaED2qyDUV9GQxmT9sdoyRp9_q5
|
|
|
91
91
|
ddi_fw/utils/py7zr_helper.py,sha256=gOqaFIyJvTjUM-btO2x9AQ69jZOS8PoKN0wetYIckJw,4747
|
|
92
92
|
ddi_fw/utils/utils.py,sha256=szwnxMTDRrZoeNRyDuf3aCbtzriwtaRk4mHSH3asLdA,4301
|
|
93
93
|
ddi_fw/utils/zip_helper.py,sha256=YRZA4tKZVBJwGQM0_WK6L-y5MoqkKoC-nXuuHK6CU9I,5567
|
|
94
|
-
ddi_fw-0.0.
|
|
95
|
-
ddi_fw-0.0.
|
|
96
|
-
ddi_fw-0.0.
|
|
97
|
-
ddi_fw-0.0.
|
|
94
|
+
ddi_fw-0.0.127.dist-info/METADATA,sha256=HwCn3w63ygXynQWJopR8pf2ltuqBimqZB-Sk-zxTmk8,1965
|
|
95
|
+
ddi_fw-0.0.127.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
|
|
96
|
+
ddi_fw-0.0.127.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
|
|
97
|
+
ddi_fw-0.0.127.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|