[Bug]: TypeError("'float' object is not iterable")

[945432957]

Is there an existing issue for the same bug?

• I have checked the existing issues.

RAGFlow workspace code commit ID

d683644

RAGFlow image version

v0.17.0

Other environment information

Actual behavior

Expected behavior

query chunk

Steps to reproduce

1.upload docments
2.parse doc
3.retrieval test

Additional information

No response

[Alixhan]

Same error at Agent .

2025-03-07 15:14:53,413 ERROR 1197351 LLMBundle.encode_queries can't update token usage for 11c27460f98a11ef88d7fd1895514194/EMBEDDING used_tokens: 19
2025-03-07 15:14:53,496 INFO 1197351 POST http://localhost:1200/ragflow_11c27460f98a11ef88d7fd1895514194/_search [status:200 duration:0.010s]
2025-03-07 15:14:53,664 ERROR 1197351 Canvas.run got exception: 'float' object is not iterable
Traceback (most recent call last):
File "/home/ragflow/agent/canvas.py", line 222, in prepare2run
ans = cpn.run(self.history, **kwargs)
File "/home/ragflow/agent/component/base.py", line 420, in run
raise e
File "/home/ragflow/agent/component/base.py", line 416, in run
res = self._run(history, **kwargs)
File "/home/ragflow/agent/component/retrieval.py", line 71, in _run
kbinfos = settings.retrievaler.retrieval(query, embd_mdl, kbs[0].tenant_id, self._param.kb_ids,
File "<@beartype(rag.nlp.search.Dealer.retrieval) at 0x7f96c5285120>", line 35, in retrieval
File "/home/ragflow/rag/nlp/search.py", line 366, in retrieval
sim, tsim, vsim = self.rerank_by_model(rerank_mdl,
File "<@beartype(rag.nlp.search.Dealer.rerank_by_model) at 0x7f96c5285000>", line 35, in rerank_by_model
File "/home/ragflow/rag/nlp/search.py", line 327, in rerank_by_model
vtsim, _ = rerank_mdl.similarity(query, [rmSpace(" ".join(tks)) for tks in ins_tw])
File "<@beartype(api.db.services.llm_service.LLMBundle.similarity) at 0x7f96b5b4d870>", line 50, in similarity
File "/home/ragflow/api/db/services/llm_service.py", line 256, in similarity
sim, used_tokens = self.mdl.similarity(query, texts)
File "<@beartype(rag.llm.rerank_model.DefaultRerank.similarity) at 0x7f96b5b2a200>", line 50, in similarity
File "/home/ragflow/rag/llm/rerank_model.py", line 148, in similarity
res = self._process_batch(pairs, max_batch_size=batch_size)
File "/home/ragflow/rag/llm/rerank_model.py", line 116, in _process_batch
res.extend(batch_scores)
TypeError: 'float' object is not iterable
Traceback (most recent call last):
File "/home/ragflow/api/apps/canvas_app.py", line 135, in sse
for ans in canvas.run(stream=True):
File "/home/ragflow/agent/canvas.py", line 271, in run
for m in prepare2run(downstream):
File "/home/ragflow/agent/canvas.py", line 227, in prepare2run
raise e
File "/home/ragflow/agent/canvas.py", line 222, in prepare2run
ans = cpn.run(self.history, **kwargs)
File "/home/ragflow/agent/component/base.py", line 420, in run
raise e
File "/home/ragflow/agent/component/base.py", line 416, in run
res = self._run(history, **kwargs)
File "/home/ragflow/agent/component/retrieval.py", line 71, in _run
kbinfos = settings.retrievaler.retrieval(query, embd_mdl, kbs[0].tenant_id, self._param.kb_ids,
File "<@beartype(rag.nlp.search.Dealer.retrieval) at 0x7f96c5285120>", line 35, in retrieval
File "/home/ragflow/rag/nlp/search.py", line 366, in retrieval
sim, tsim, vsim = self.rerank_by_model(rerank_mdl,
File "<@beartype(rag.nlp.search.Dealer.rerank_by_model) at 0x7f96c5285000>", line 35, in rerank_by_model
File "/home/ragflow/rag/nlp/search.py", line 327, in rerank_by_model
vtsim, _ = rerank_mdl.similarity(query, [rmSpace(" ".join(tks)) for tks in ins_tw])
File "<@beartype(api.db.services.llm_service.LLMBundle.similarity) at 0x7f96b5b4d870>", line 50, in similarity
File "/home/ragflow/api/db/services/llm_service.py", line 256, in similarity
sim, used_tokens = self.mdl.similarity(query, texts)
File "<@beartype(rag.llm.rerank_model.DefaultRerank.similarity) at 0x7f96b5b2a200>", line 50, in similarity
File "/home/ragflow/rag/llm/rerank_model.py", line 148, in similarity
res = self._process_batch(pairs, max_batch_size=batch_size)
File "/home/ragflow/rag/llm/rerank_model.py", line 116, in _process_batch
res.extend(batch_scores)
TypeError: 'float' object is not iterable
2025-03-07 15:14:53,739 INFO 1197351 127.0.0.1 - - [07/Mar/2025 15:14:53] "GET /v1/canvas/get/4cc60c54faff11efb52bf3c0fb4d1d45 HTTP/1.1" 200 -

[KevinHuSh]

Pull the nightly version of docker image. It's been fixed there.

[Alixhan]

Pull the nightly version of docker image. It's been fixed there.

I'll try, tks bro.