pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix plainPdf bugs (#152)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-26 15:11:07 +08:00
committed by GitHub
parent 75f7c6da2f
commit da21320b88
13 changed files with 36 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
api/apps/conversation_app.py
View File

@ -183,9 +183,7 @@ def chat(dialog, messages, **kwargs):
## try to use sql if field mapping is good to go
if field_map:
chat_logger.info("Use SQL to retrieval:{}".format(questions[-1]))
markdown_tbl, chunks = use_sql(questions[-1], field_map, dialog.tenant_id, chat_mdl)
if markdown_tbl:
return {"answer": markdown_tbl, "reference": {"chunks": chunks, "doc_aggs": []}}
return use_sql(questions[-1], field_map, dialog.tenant_id, chat_mdl)
prompt_config = dialog.prompt_config
for p in prompt_config["parameters"]:
@ -311,7 +309,7 @@ def use_sql(question, field_map, tenant_id, chat_mdl):
clmn_idx = [ii for ii in range(len(tbl["columns"])) if ii not in (docid_idx | docnm_idx)]
# compose markdown table
clmns = "|"+"|".join([re.sub(r"(/.*|（[^（）]+）)", "", field_map.get(tbl["columns"][i]["name"], tbl["columns"][i]["name"])) for i in clmn_idx]) + ("|原文|" if docid_idx and docid_idx else "|")
clmns = "|"+"|".join([re.sub(r"(/.*|（[^（）]+）)", "", field_map.get(tbl["columns"][i]["name"], tbl["columns"][i]["name"])) for i in clmn_idx]) + ("|Source|" if docid_idx and docid_idx else "|")
line = "|"+"|".join(["------" for _ in range(len(clmn_idx))]) + ("|------|" if docid_idx and docid_idx else "")
rows = ["|"+"|".join([rmSpace(str(r[i])) for i in clmn_idx]).replace("None", " ") + "|" for r in tbl["rows"]]
if not docid_idx or not docnm_idx:
@ -322,4 +320,8 @@ def use_sql(question, field_map, tenant_id, chat_mdl):
rows = re.sub(r"T[0-9]{2}:[0-9]{2}:[0-9]{2}(\.[0-9]+Z)?\|", "|", rows)
docid_idx = list(docid_idx)[0]
docnm_idx = list(docnm_idx)[0]
return "\n".join([clmns, line, rows]), [{"doc_id": r[docid_idx], "docnm_kwd": r[docnm_idx]} for r in tbl["rows"]]
return {
"answer": "\n".join([clmns, line, rows]),
"reference": {"chunks": [{"doc_id": r[docid_idx], "docnm_kwd": r[docnm_idx]} for r in tbl["rows"]],
"doc_aggs": [{"doc_id": r[docid_idx], "doc_name": r[docnm_idx], "count": 1} for r in tbl["rows"]]}
}