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

add function: upload and parse (#1889)

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

#1880
### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Kevin Hu
2024-08-09 16:20:02 +08:00
committed by GitHub
parent 6529c764c9
commit e3cf14a3c9
8 changed files with 255 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
api/db/services/dialog_service.py
View File

@ -104,7 +104,11 @@ def chat(dialog, messages, stream=True, **kwargs):
is_kg = all([kb.parser_id == ParserType.KG for kb in kbs])
retr = retrievaler if not is_kg else kg_retrievaler
questions = [m["content"] for m in messages if m["role"] == "user"]
questions = [m["content"] for m in messages if m["role"] == "user"][-3:]
attachments = kwargs["doc_ids"].split(",") if "doc_ids" in kwargs else None
if "doc_ids" in messages[-1]:
attachments = messages[-1]["doc_ids"]
embd_mdl = LLMBundle(dialog.tenant_id, LLMType.EMBEDDING, embd_nms[0])
if llm_id2llm_type(dialog.llm_id) == "image2text":
chat_mdl = LLMBundle(dialog.tenant_id, LLMType.IMAGE2TEXT, dialog.llm_id)
@ -144,7 +148,7 @@ def chat(dialog, messages, stream=True, **kwargs):
kbinfos = retr.retrieval(" ".join(questions), embd_mdl, dialog.tenant_id, dialog.kb_ids, 1, dialog.top_n,
dialog.similarity_threshold,
dialog.vector_similarity_weight,
doc_ids=kwargs["doc_ids"].split(",") if "doc_ids" in kwargs else None,
doc_ids=attachments,
top=dialog.top_k, aggs=False, rerank_mdl=rerank_mdl)
knowledges = [ck["content_with_weight"] for ck in kbinfos["chunks"]]
#self-rag
@ -153,7 +157,7 @@ def chat(dialog, messages, stream=True, **kwargs):
kbinfos = retr.retrieval(" ".join(questions), embd_mdl, dialog.tenant_id, dialog.kb_ids, 1, dialog.top_n,
dialog.similarity_threshold,
dialog.vector_similarity_weight,
doc_ids=kwargs["doc_ids"].split(",") if "doc_ids" in kwargs else None,
doc_ids=attachments,
top=dialog.top_k, aggs=False, rerank_mdl=rerank_mdl)
knowledges = [ck["content_with_weight"] for ck in kbinfos["chunks"]]