github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4576] Tried Agentic chucking using Ollama but got error #28631

New Issue
Open
opened 2026-04-22 07:05:56 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 07:05:56 -05:00
Owner
Copy Link

Originally created by @arunkumarm-git on GitHub (May 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4576

What is the issue?

Code:
from langchain_community.llms import Ollama
from langchain.chains import create_extraction_chain_pydantic
from langchain_core.pydantic_v1 import BaseModel
from typing import Optional, List

llm = Ollama(model='llama3')
from langchain import hub
prompt = hub.pull("wfh/proposal-indexing")

runnable = prompt | llm

class Sentences(BaseModel):
sentences: List[str]

Extraction

extraction_chain = create_extraction_chain_pydantic(pydantic_schema=Sentences, llm=llm)

def get_propositions(text):
runnable_output = runnable.invoke({
"input": text
}).content

propositions = extraction_chain.run(runnable_output)[0].sentences
return propositions

essay_propositions = []

for i, para in enumerate(pdf_text_document):
propositions = get_propositions(para)

essay_propositions.extend(propositions)

Error:
File g:\AI arbiter V2\env\Lib\site-packages\urllib3\connectionpool.py:715, in HTTPConnectionPool.urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
714 # Make the request on the httplib connection object.
--> 715 httplib_response = self._make_request(
716 conn,
717 method,
718 url,
719 timeout=timeout_obj,
720 body=body,
721 headers=headers,
722 chunked=chunked,
723 )
725 # If we're going to release the connection in finally:, then
726 # the response doesn't need to know about the connection. Otherwise
727 # it will also try to release it and we'll have a double-release
728 # mess.

File g:\AI arbiter V2\env\Lib\site-packages\urllib3\connectionpool.py:467, in HTTPConnectionPool._make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
463 except BaseException as e:
464 # Remove the TypeError from the exception chain in
465 # Python 3 (including for exceptions like SystemExit).
466 # Otherwise it looks like a bug in the code.
--> 467 six.raise_from(e, None)
468 except (SocketTimeout, BaseSSLError, SocketError) as e:
...
503 except MaxRetryError as e:
504 if isinstance(e.reason, ConnectTimeoutError):
505 # TODO: Remove this in 3.0.0: see #2811

ConnectionError: ('Connection aborted.', ConnectionResetError(10054, 'An existing connection was forcibly closed by the remote host', None, 10054, None))

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.1.30

Originally created by @arunkumarm-git on GitHub (May 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4576 ### What is the issue? Code: from langchain_community.llms import Ollama from langchain.chains import create_extraction_chain_pydantic from langchain_core.pydantic_v1 import BaseModel from typing import Optional, List llm = Ollama(model='llama3') from langchain import hub prompt = hub.pull("wfh/proposal-indexing") runnable = prompt | llm class Sentences(BaseModel): sentences: List[str] # Extraction extraction_chain = create_extraction_chain_pydantic(pydantic_schema=Sentences, llm=llm) def get_propositions(text): runnable_output = runnable.invoke({ "input": text }).content propositions = extraction_chain.run(runnable_output)[0].sentences return propositions essay_propositions = [] for i, para in enumerate(pdf_text_document): propositions = get_propositions(para) essay_propositions.extend(propositions) Error: File g:\AI arbiter V2\env\Lib\site-packages\urllib3\connectionpool.py:715, in HTTPConnectionPool.urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw) [714](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:714) # Make the request on the httplib connection object. --> [715](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:715) httplib_response = self._make_request( [716](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:716) conn, [717](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:717) method, [718](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:718) url, [719](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:719) timeout=timeout_obj, [720](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:720) body=body, [721](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:721) headers=headers, [722](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:722) chunked=chunked, [723](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:723) ) [725](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:725) # If we're going to release the connection in ``finally:``, then [726](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:726) # the response doesn't need to know about the connection. Otherwise [727](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:727) # it will also try to release it and we'll have a double-release [728](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:728) # mess. File g:\AI arbiter V2\env\Lib\site-packages\urllib3\connectionpool.py:467, in HTTPConnectionPool._make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw) [463](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:463) except BaseException as e: [464](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:464) # Remove the TypeError from the exception chain in [465](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:465) # Python 3 (including for exceptions like SystemExit). [466](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:466) # Otherwise it looks like a bug in the code. --> [467](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:467) six.raise_from(e, None) [468](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/urllib3/connectionpool.py:468) except (SocketTimeout, BaseSSLError, SocketError) as e: ... [503](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/requests/adapters.py:503) except MaxRetryError as e: [504](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/requests/adapters.py:504) if isinstance(e.reason, ConnectTimeoutError): [505](file:///G:/AI%20arbiter%20V2/env/Lib/site-packages/requests/adapters.py:505) # TODO: Remove this in 3.0.0: see #2811 ConnectionError: ('Connection aborted.', ConnectionResetError(10054, 'An existing connection was forcibly closed by the remote host', None, 10054, None)) ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.1.30
GiteaMirror added the bug label 2026-04-22 07:05:56 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#28631
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?