github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4509] API HTTP code: 500, "error":"failed to generate embedding with langchain #49337

New Issue
Open
opened 2026-04-28 11:16:55 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-28 11:16:55 -05:00
Owner
Copy Link

Originally created by @buaa39055211 on GitHub (May 18, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4509

What is the issue?

after version 0.1.32 of Ollama,there always have a bug with the api of embedding
the embedding model I used is "smartcreation/bge-large-zh-v1.5",and dztech/bge-large-zh:v1.5 pulled from ollama

`
from langchain_community.embeddings import OllamaEmbeddings
from langchain_community.document_loaders import (
CSVLoader,
UnstructuredWordDocumentLoader,
)
from langchain_community.vectorstores import Qdrant
from qdrant_client import QdrantClient
base_url="http://127.0.0.1:11434")
embeddings = OllamaEmbeddings(model="dztech/bge-large-zh:v1.5",base_url=base_url)
LOADER_MAPPING = {
".csv": (CSVLoader, {}),
# ".docx": (Docx2txtLoader, {}),
".doc": (UnstructuredWordDocumentLoader, {"mode": "elements"}),
".docx": (UnstructuredWordDocumentLoader, {}),}
def split(uploaded_file_name):
# Create embeddings
print("Creating new vectorstore")
texts = process_documents(uploaded_file_name)
print(f"Creating embeddings. May take some minutes...")
db = Qdrant.from_documents(texts, embedding=embeddings,url='localhost:7541', collection_name=uploaded_file_name)
print(uploaded_file_name)
query = "insert"
docs = db.similarity_search(query)
print(docs[0].page_content)

`
File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/vectorstores/qdrant.py", line 2037, in _embed_texts
embeddings = self.embeddings.embed_documents(list(texts))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 204, in embed_documents
embeddings = self._embed(instruction_pairs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 192, in _embed
return [self.process_emb_response(prompt) for prompt in iter]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 192, in
return [self.process_emb_response(prompt) for prompt in iter]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 166, in _process_emb_response
raise ValueError(
ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"}

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.33-0.1.38

Originally created by @buaa39055211 on GitHub (May 18, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4509 ### What is the issue? after version 0.1.32 of Ollama,there always have a bug with the api of embedding the embedding model I used is "smartcreation/bge-large-zh-v1.5",and dztech/bge-large-zh:v1.5 pulled from ollama ` from langchain_community.embeddings import OllamaEmbeddings from langchain_community.document_loaders import ( CSVLoader, UnstructuredWordDocumentLoader, ) from langchain_community.vectorstores import Qdrant from qdrant_client import QdrantClient base_url="http://127.0.0.1:11434") embeddings = OllamaEmbeddings(model="dztech/bge-large-zh:v1.5",base_url=base_url) LOADER_MAPPING = { ".csv": (CSVLoader, {}), # ".docx": (Docx2txtLoader, {}), ".doc": (UnstructuredWordDocumentLoader, {"mode": "elements"}), ".docx": (UnstructuredWordDocumentLoader, {}),} def split(uploaded_file_name): # Create embeddings print("Creating new vectorstore") texts = process_documents(uploaded_file_name) print(f"Creating embeddings. May take some minutes...") db = Qdrant.from_documents(texts, embedding=embeddings,url='localhost:7541', collection_name=uploaded_file_name) print(uploaded_file_name) query = "insert" docs = db.similarity_search(query) print(docs[0].page_content) ` File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/vectorstores/qdrant.py", line 2037, in _embed_texts embeddings = self.embeddings.embed_documents(list(texts)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 204, in embed_documents embeddings = self._embed(instruction_pairs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 192, in _embed return [self._process_emb_response(prompt) for prompt in iter_] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 192, in <listcomp> return [self._process_emb_response(prompt) for prompt in iter_] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/mac/anaconda3/envs/ag2/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 166, in _process_emb_response raise ValueError( ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"} ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.33-0.1.38
GiteaMirror added the bugapi labels 2026-04-28 11:16:58 -05:00
GiteaMirror commented 2026-04-28 11:17:02 -05:00
Author
Owner
Copy Link

@colorfuldarkgray commented on GitHub (Aug 3, 2024):

This is not a solution but it helped in my case. What embeddings are you using now?

import chromadb import time client = chromadb.Client() collection = client.create_collection(name="A_review_of_visualisation-as-explanation_techniques")

store each document in a vector embedding database

for i, d in enumerate(all_splits): try: response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) except: print(i) time.sleep(0.5) response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) embedding = response["embedding"] collection.add( ids=[str(i)], embeddings=[embedding], documents=[d.page_content])

<!-- gh-comment-id:2267201582 --> @colorfuldarkgray commented on GitHub (Aug 3, 2024): > This is not a solution but it helped in my case. What embeddings are you using now? > > import chromadb import time client = chromadb.Client() collection = client.create_collection(name="A_review_of_visualisation-as-explanation_techniques") > > ##### store each document in a vector embedding database > for i, d in enumerate(all_splits): try: response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) except: print(i) time.sleep(0.5) response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) embedding = response["embedding"] collection.add( ids=[str(i)], embeddings=[embedding], documents=[d.page_content])
GiteaMirror commented 2026-04-28 11:17:05 -05:00
Author
Owner
Copy Link

@mokby commented on GitHub (Oct 25, 2024):

same error, did you solve it?

<!-- gh-comment-id:2436677429 --> @mokby commented on GitHub (Oct 25, 2024): same error, did you solve it?
GiteaMirror commented 2026-04-28 11:17:06 -05:00
Author
Owner
Copy Link

@colorfuldarkgray commented on GitHub (Oct 25, 2024):

This helped me, have you tried something similar?

for i, d in enumerate(all_splits): 
    try: 
        response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) 
    except: 
        time.sleep(0.5) 
        response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content)
    embedding = response["embedding"] 
    collection.add( ids=[str(i)], embeddings=[embedding], documents=[d.page_content])
<!-- gh-comment-id:2436702918 --> @colorfuldarkgray commented on GitHub (Oct 25, 2024): This helped me, have you tried something similar? ``` for i, d in enumerate(all_splits): try: response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) except: time.sleep(0.5) response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) embedding = response["embedding"] collection.add( ids=[str(i)], embeddings=[embedding], documents=[d.page_content]) ```
GiteaMirror commented 2026-04-28 11:17:09 -05:00
Author
Owner
Copy Link

@mokby commented on GitHub (Oct 25, 2024):

This helped me, have you tried something similar?

for i, d in enumerate(all_splits): 
    try: 
        response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) 
    except: 
        time.sleep(0.5) 
        response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content)
    embedding = response["embedding"] 
    collection.add( ids=[str(i)], embeddings=[embedding], documents=[d.page_content])

Thanks for you replying. When using nomic-embed-text, everything just fine, but after I changed embedding model into anything else, errors occured, I am using LightRAG by the way.

<!-- gh-comment-id:2436713030 --> @mokby commented on GitHub (Oct 25, 2024): > This helped me, have you tried something similar? > > ``` > for i, d in enumerate(all_splits): > try: > response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) > except: > time.sleep(0.5) > response = ollama.embeddings(model="nomic-embed-text", prompt=d.page_content) > embedding = response["embedding"] > collection.add( ids=[str(i)], embeddings=[embedding], documents=[d.page_content]) > ``` Thanks for you replying. When using `nomic-embed-text`, everything just fine, but after I changed embedding model into anything else, errors occured, I am using LightRAG by the way.
GiteaMirror commented 2026-04-28 11:17:11 -05:00
Author
Owner
Copy Link

@kexul commented on GitHub (Nov 2, 2024):

Same issue here.

<!-- gh-comment-id:2452875029 --> @kexul commented on GitHub (Nov 2, 2024): Same issue here.
GiteaMirror commented 2026-04-28 11:17:11 -05:00
Author
Owner
Copy Link

@kexul commented on GitHub (Nov 2, 2024):

C:\a\ollama\ollama\llm\llama.cpp\ggml\src\ggml.c:13289: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed

<!-- gh-comment-id:2452875418 --> @kexul commented on GitHub (Nov 2, 2024): C:\a\ollama\ollama\llm\llama.cpp\ggml\src\ggml.c:13289: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed
GiteaMirror commented 2026-04-28 11:17:12 -05:00
Author
Owner
Copy Link

@kexul commented on GitHub (Nov 2, 2024):

As this suggested, https://github.com/ollama/ollama/issues/7441 we should downgrade ollama to 0.3.13.

<!-- gh-comment-id:2452876099 --> @kexul commented on GitHub (Nov 2, 2024): As this suggested, https://github.com/ollama/ollama/issues/7441 we should downgrade ollama to 0.3.13.
GiteaMirror commented 2026-04-28 11:17:13 -05:00
Author
Owner
Copy Link

@mokby commented on GitHub (Nov 4, 2024):

As this suggested, #7441 we should downgrade ollama to 0.3.13.

Thanks, will try that later

<!-- gh-comment-id:2453675349 --> @mokby commented on GitHub (Nov 4, 2024): > As this suggested, #7441 we should downgrade ollama to 0.3.13. Thanks, will try that later
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 api 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#49337
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?