pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 12:32:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: waitForResponse component. (#11172)

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

#10056

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Kevin Hu
2025-11-11 16:58:47 +08:00
committed by GitHub
parent 522c7b7ac6
commit f441f8ffc2
9 changed files with 92 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rag/llm/__init__.py
View File

@ -37,7 +37,7 @@ class SupportedLiteLLMProvider(StrEnum):
TogetherAI = "TogetherAI"
Anthropic = "Anthropic"
Ollama = "Ollama"
Meituan = "Meituan"
LongCat = "LongCat"
CometAPI = "CometAPI"
SILICONFLOW = "SILICONFLOW"
OpenRouter = "OpenRouter"
@ -56,7 +56,7 @@ FACTORY_DEFAULT_BASE_URL = {
SupportedLiteLLMProvider.Dashscope: "https://dashscope.aliyuncs.com/compatible-mode/v1",
SupportedLiteLLMProvider.Moonshot: "https://api.moonshot.cn/v1",
SupportedLiteLLMProvider.Ollama: "",
SupportedLiteLLMProvider.Meituan: "https://api.longcat.chat/openai",
SupportedLiteLLMProvider.LongCat: "https://api.longcat.chat/openai",
SupportedLiteLLMProvider.CometAPI: "https://api.cometapi.com/v1",
SupportedLiteLLMProvider.SILICONFLOW: "https://api.siliconflow.cn/v1",
SupportedLiteLLMProvider.OpenRouter: "https://openrouter.ai/api/v1",
@ -87,7 +87,7 @@ LITELLM_PROVIDER_PREFIX = {
SupportedLiteLLMProvider.TogetherAI: "together_ai/",
SupportedLiteLLMProvider.Anthropic: "", # don't need a prefix
SupportedLiteLLMProvider.Ollama: "ollama_chat/",
SupportedLiteLLMProvider.Meituan: "openai/",
SupportedLiteLLMProvider.LongCat: "openai/",
SupportedLiteLLMProvider.CometAPI: "openai/",
SupportedLiteLLMProvider.SILICONFLOW: "openai/",
SupportedLiteLLMProvider.OpenRouter: "openai/",

2
rag/llm/chat_model.py
View File

@ -1390,7 +1390,7 @@ class LiteLLMBase(ABC):
"TogetherAI",
"Anthropic",
"Ollama",
"Meituan",
"LongCat",
"CometAPI",
"SILICONFLOW",
"OpenRouter",

2
rag/raptor.py
View File

@ -97,7 +97,7 @@ class RecursiveAbstractiveProcessing4TreeOrganizedRetrieval:
async def __call__(self, chunks, random_state, callback=None, task_id: str = ""):
if len(chunks) <= 1:
return []
chunks = [(s, a) for s, a in chunks if s and len(a) > 0]
chunks = [(s, a) for s, a in chunks if s and a and len(a) > 0]
layers = [(0, len(chunks))]
start, end = 0, len(chunks)

92
rag/svr/task_executor.py
View File

@ -642,47 +642,64 @@ async def run_raptor_for_kb(row, kb_parser_config, chat_mdl, embd_mdl, vector_si
fake_doc_id = GRAPH_RAPTOR_FAKE_DOC_ID
raptor_config = kb_parser_config.get("raptor", {})
chunks = []
vctr_nm = "q_%d_vec"%vector_size
for doc_id in doc_ids:
for d in settings.retriever.chunk_list(doc_id, row["tenant_id"], [str(row["kb_id"])],
fields=["content_with_weight", vctr_nm],
sort_by_position=True):
chunks.append((d["content_with_weight"], np.array(d[vctr_nm])))
raptor = Raptor(
raptor_config.get("max_cluster", 64),
chat_mdl,
embd_mdl,
raptor_config["prompt"],
raptor_config["max_token"],
raptor_config["threshold"],
)
original_length = len(chunks)
chunks = await raptor(chunks, kb_parser_config["raptor"]["random_seed"], callback, row["id"])
doc = {
"doc_id": fake_doc_id,
"kb_id": [str(row["kb_id"])],
"docnm_kwd": row["name"],
"title_tks": rag_tokenizer.tokenize(row["name"]),
"raptor_kwd": "raptor"
}
if row["pagerank"]:
doc[PAGERANK_FLD] = int(row["pagerank"])
res = []
tk_count = 0
for content, vctr in chunks[original_length:]:
d = copy.deepcopy(doc)
d["id"] = xxhash.xxh64((content + str(fake_doc_id)).encode("utf-8")).hexdigest()
d["create_time"] = str(datetime.now()).replace("T", " ")[:19]
d["create_timestamp_flt"] = datetime.now().timestamp()
d[vctr_nm] = vctr.tolist()
d["content_with_weight"] = content
d["content_ltks"] = rag_tokenizer.tokenize(content)
d["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(d["content_ltks"])
res.append(d)
tk_count += num_tokens_from_string(content)
async def generate(chunks):
nonlocal tk_count, res
raptor = Raptor(
raptor_config.get("max_cluster", 64),
chat_mdl,
embd_mdl,
raptor_config["prompt"],
raptor_config["max_token"],
raptor_config["threshold"],
)
original_length = len(chunks)
chunks = await raptor(chunks, kb_parser_config["raptor"]["random_seed"], callback, row["id"])
doc = {
"doc_id": fake_doc_id,
"kb_id": [str(row["kb_id"])],
"docnm_kwd": row["name"],
"title_tks": rag_tokenizer.tokenize(row["name"]),
"raptor_kwd": "raptor"
}
if row["pagerank"]:
doc[PAGERANK_FLD] = int(row["pagerank"])
for content, vctr in chunks[original_length:]:
d = copy.deepcopy(doc)
d["id"] = xxhash.xxh64((content + str(fake_doc_id)).encode("utf-8")).hexdigest()
d["create_time"] = str(datetime.now()).replace("T", " ")[:19]
d["create_timestamp_flt"] = datetime.now().timestamp()
d[vctr_nm] = vctr.tolist()
d["content_with_weight"] = content
d["content_ltks"] = rag_tokenizer.tokenize(content)
d["content_sm_ltks"] = rag_tokenizer.fine_grained_tokenize(d["content_ltks"])
res.append(d)
tk_count += num_tokens_from_string(content)
if raptor_config.get("scope", "file") == "file":
for x, doc_id in enumerate(doc_ids):
chunks = []
for d in settings.retriever.chunk_list(doc_id, row["tenant_id"], [str(row["kb_id"])],
fields=["content_with_weight", vctr_nm],
sort_by_position=True):
chunks.append((d["content_with_weight"], np.array(d[vctr_nm])))
callback(progress=(x+1.)/len(doc_ids))
await generate(chunks)
else:
chunks = []
for doc_id in doc_ids:
for d in settings.retriever.chunk_list(doc_id, row["tenant_id"], [str(row["kb_id"])],
fields=["content_with_weight", vctr_nm],
sort_by_position=True):
chunks.append((d["content_with_weight"], np.array(d[vctr_nm])))
await generate(chunks)
return res, tk_count
@ -795,6 +812,7 @@ async def do_handle_task(task):
"threshold": 0.1,
"max_cluster": 64,
"random_seed": 0,
"scope": "file"
},
}
)