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

Feat: Add question parameter to edit chunk modal (#3875)

Browse Source 
### What problem does this PR solve?

Close #3873

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Kevin Hu
2024-12-05 14:51:19 +08:00
committed by GitHub
parent b502dc7399
commit 56f473b680
8 changed files with 55 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
api/apps/chunk_app.py
View File

@ -68,6 +68,7 @@ def list_chunk():
"doc_id": sres.field[id]["doc_id"],
"docnm_kwd": sres.field[id]["docnm_kwd"],
"important_kwd": sres.field[id].get("important_kwd", []),
"question_kwd": sres.field[id].get("question_kwd", []),
"image_id": sres.field[id].get("img_id", ""),
"available_int": sres.field[id].get("available_int", 1),
"positions": json.loads(sres.field[id].get("position_list", "[]")),
@ -115,7 +116,7 @@ def get():
@manager.route('/set', methods=['POST'])
@login_required
@validate_request("doc_id", "chunk_id", "content_with_weight",
"important_kwd")
"important_kwd", "question_kwd")
def set():
req = request.json
d = {
@ -125,6 +126,8 @@ def set():
d["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(d["content_ltks"])
d["important_kwd"] = req["important_kwd"]
d["important_tks"] = rag_tokenizer.tokenize(" ".join(req["important_kwd"]))
d["question_kwd"] = req["question_kwd"]
d["question_tks"] = rag_tokenizer.tokenize("\n".join(req["question_kwd"]))
if "available_int" in req:
d["available_int"] = req["available_int"]
@ -152,7 +155,7 @@ def set():
d = beAdoc(d, arr[0], arr[1], not any(
[rag_tokenizer.is_chinese(t) for t in q + a]))
v, c = embd_mdl.encode([doc.name, req["content_with_weight"]])
v, c = embd_mdl.encode([doc.name, req["content_with_weight"] if not d["question_kwd"] else "\n".join(d["question_kwd"])])
v = 0.1 * v[0] + 0.9 * v[1] if doc.parser_id != ParserType.QA else v[1]
d["q_%d_vec" % len(v)] = v.tolist()
settings.docStoreConn.update({"id": req["chunk_id"]}, d, search.index_name(tenant_id), doc.kb_id)
@ -213,6 +216,8 @@ def create():
d["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(d["content_ltks"])
d["important_kwd"] = req.get("important_kwd", [])
d["important_tks"] = rag_tokenizer.tokenize(" ".join(req.get("important_kwd", [])))
d["question_kwd"] = req.get("question_kwd", [])
d["question_tks"] = rag_tokenizer.tokenize("\n".join(req.get("question_kwd", [])))
d["create_time"] = str(datetime.datetime.now()).replace("T", " ")[:19]
d["create_timestamp_flt"] = datetime.datetime.now().timestamp()
@ -237,7 +242,7 @@ def create():
embd_id = DocumentService.get_embd_id(req["doc_id"])
embd_mdl = LLMBundle(tenant_id, LLMType.EMBEDDING.value, embd_id)
v, c = embd_mdl.encode([doc.name, req["content_with_weight"]])
v, c = embd_mdl.encode([doc.name, req["content_with_weight"] if not d["question_kwd"] else "\n".join(d["question_kwd"])])
v = 0.1 * v[0] + 0.9 * v[1]
d["q_%d_vec" % len(v)] = v.tolist()
settings.docStoreConn.insert([d], search.index_name(tenant_id), doc.kb_id)