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 #1577] ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"} #47378

New Issue
Closed
opened 2026-04-28 03:38:56 -05:00 by GiteaMirror · 11 comments
GiteaMirror commented 2026-04-28 03:38:56 -05:00
Owner
Copy Link

Originally created by @doanaktar on GitHub (Dec 18, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1577

When i'm trying ollama for document chat i get api error when it tries to create vectorstore.

from langchain.llms import Ollama
from langchain.document_loaders import WebBaseLoader
from langchain.embeddings import OllamaEmbeddings
from langchain.vectorstores import Chroma
from langchain.chains import RetrievalQA
from langchain.text_splitter import RecursiveCharacterTextSplitter

ollama = Ollama(base_url='http://localhost:11434',
model="llama2")
print(ollama("why is the sky blue"))

loader = WebBaseLoader("https://www.gutenberg.org/files/1727/1727-h/1727-h.htm")
data = loader.load()

text_splitter=RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
all_splits = text_splitter.split_documents(data)
oembed = OllamaEmbeddings(base_url="http://localhost:11434", model="llama2")

print("embedding: ", oembed)
vectorstore = Chroma.from_documents(documents=all_splits, embedding=oembed)

question="Who is Neleus and who is in Neleus' family?"
docs = vectorstore.similarity_search(question)
len(docs)

qachain=RetrievalQA.from_chain_type(ollama, retriever=vectorstore.as_retriever())
qachain({"query": question})

In my terminal the prints look like this:

The sky appears blue because of a phenomenon called Rayleigh scattering, which occurs when sunlight enters Earth's atmosphere. The sunlight encounters tiny molecules of gases such as nitrogen and oxygen in the air, which scatter the light in all directions.

The shortest wavelengths of light, such as violet and blue, are scattered more than other colors, such as red and orange, because they have a shorter wave length. This means that these colors are dispersed throughout the atmosphere, giving the sky its blue appearance.

Other factors can also affect the color of the sky, such as the presence of dust, water vapor, and pollutants in the air. For example, during sunrise and sunset, the sky may take on hues of red, orange, and pink due to the scattering of light by atmospheric particles.

It's worth noting that the color of the sky can also vary depending on the observer's location and the time of day. For example, the sky may appear more blue or gray if you are near a body of water or in an area with a high level of air pollution.

In summary, the sky appears blue because of the way light interacts with the tiny molecules of gases in the air, known as Rayleigh scattering. This phenomenon scatters shorter wavelengths of light, such as blue and violet, more than longer wavelengths, giving the sky its characteristic blue color.
embedding:  base_url='http://localhost:11434' model='llama2' embed_instruction='passage: ' query_instruction='query: ' mirostat=None mirostat_eta=None mirostat_tau=None num_ctx=None num_gpu=None num_thread=None repeat_last_n=None repeat_penalty=None temperature=None stop=None tfs_z=None top_k=None top_p=None model_kwargs=None
Traceback (most recent call last):
  File "olama.py", line 23, in <module>
    vectorstore = Chroma.from_documents(documents=all_splits, embedding=oembed)
  File "./Env/chatbot/lib/python3.8/site-packages/langchain/vectorstores/chroma.py", line 771, in from_documents
    return cls.from_texts(
  File "./Env/chatbot/lib/python3.8/site-packages/langchain/vectorstores/chroma.py", line 729, in from_texts
    chroma_collection.add_texts(
  File "./Env/chatbot/lib/python3.8/site-packages/langchain/vectorstores/chroma.py", line 275, in add_texts
    embeddings = self._embedding_function.embed_documents(texts)
  File "./Env/chatbot/lib/python3.8/site-packages/langchain/embeddings/ollama.py", line 190, in embed_documents
    embeddings = self._embed(instruction_pairs)
  File "./Env/chatbot/lib/python3.8/site-packages/langchain/embeddings/ollama.py", line 175, in _embed
    embeddings = self._process_emb_response(prompt)
  File "./Env/chatbot/lib/python3.8/site-packages/langchain/embeddings/ollama.py", line 160, in _process_emb_response
    raise ValueError(
ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"}

And even i try to get embeddings via api

curl -X POST http://localhost:11434/api/embeddings -d '{
    "model": "llama2",
    "prompt": "hello, how are you?"
}'

My embeddings looks like this:

{"embedding":[0.713813066482544,-1.8217487335205078,0.48764699697494507,-0.8590573668479919,-0.7165888547897339,0.09285138547420502,-0.06305933743715286,0.8703135251998901,-0.7629101872444153,0.40360304713249207,1.6491974592208862,-0.7351164817810059,0.9032987356185913,1.0884538888931274,0.754738986492157,-0.0351458303630352,-0.2696535289287567,0.030562296509742737,-0.5470462441444397,-0.7511221170425415,1.6396052837371826,-2.254915714263916,-0.2600090503692627,-2.861804723739624,-0.31693896651268005,-1.0240172147750854,-0.7449401617050171,-2.3529539108276367,1.3769773244857788,-0.15259328484535217,1.564031958580017,0.33758652210235596,-1.2046291828155518,2.713618040084839,-0.22524534165859222,0.08619225025177002,0.5370852947235107,1.7855254411697388,-0.06518085300922394,-0.0628420040011406,0.5781055092811584,-4.234992504119873,-1.2907594442367554,-0.1936117261648178,1.3087000846862793,0.14808768033981323,-1.689073085784912,-3.103379011154175,0.5116130709648132,-1.674410104751587,0.026191502809524536,0.31160175800323486,1.843047022819519,-0.754763662815094,2.64321231842041,-0.9525578618049622,1.4135092496871948,1.014215350151062,1.701998233795166,0.35821205377578735,-4.310467720031738,1.3969742059707642,-0.3026293218135834,1.1710561513900757,-3.1511785984039307,-0.9500783681869507,0.25463706254959106,0.2536858320236206,0.2566526234149933,-0.8113981485366821,1.434630274772644,-0.41049930453300476,1.3408557176589966,0.3780902028083801,-2.971435546875,1.556931495666504,2.2950439453125,-2.0468714237213135,-1.6436930894851685,-0.6824514269828796,0.2970106601715088,0.48574963212013245,1.3311458826065063,-1.2823209762573242,-1.0872153043746948,1.0507322549819946,1.6134350299835205,0.44947174191474915,0.14205259084701538,-1.4551608562469482,-0.43960702419281006,-1.6097815036773682,-3.165051221847534,0.6144835352897644,1.2260065078735352,0.8544708490371704,-0.5544838905334473,-1.207687258720398,0.3186914324760437,-0.9924833178520203,0.48585525155067444,-0.987743616104126,-1.0047131776809692...
Originally created by @doanaktar on GitHub (Dec 18, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1577 When i'm trying ollama for document chat i get api error when it tries to create vectorstore. ```python from langchain.llms import Ollama from langchain.document_loaders import WebBaseLoader from langchain.embeddings import OllamaEmbeddings from langchain.vectorstores import Chroma from langchain.chains import RetrievalQA from langchain.text_splitter import RecursiveCharacterTextSplitter ollama = Ollama(base_url='http://localhost:11434', model="llama2") print(ollama("why is the sky blue")) loader = WebBaseLoader("https://www.gutenberg.org/files/1727/1727-h/1727-h.htm") data = loader.load() text_splitter=RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0) all_splits = text_splitter.split_documents(data) oembed = OllamaEmbeddings(base_url="http://localhost:11434", model="llama2") print("embedding: ", oembed) vectorstore = Chroma.from_documents(documents=all_splits, embedding=oembed) question="Who is Neleus and who is in Neleus' family?" docs = vectorstore.similarity_search(question) len(docs) qachain=RetrievalQA.from_chain_type(ollama, retriever=vectorstore.as_retriever()) qachain({"query": question}) ``` In my terminal the prints look like this: ```terminal The sky appears blue because of a phenomenon called Rayleigh scattering, which occurs when sunlight enters Earth's atmosphere. The sunlight encounters tiny molecules of gases such as nitrogen and oxygen in the air, which scatter the light in all directions. The shortest wavelengths of light, such as violet and blue, are scattered more than other colors, such as red and orange, because they have a shorter wave length. This means that these colors are dispersed throughout the atmosphere, giving the sky its blue appearance. Other factors can also affect the color of the sky, such as the presence of dust, water vapor, and pollutants in the air. For example, during sunrise and sunset, the sky may take on hues of red, orange, and pink due to the scattering of light by atmospheric particles. It's worth noting that the color of the sky can also vary depending on the observer's location and the time of day. For example, the sky may appear more blue or gray if you are near a body of water or in an area with a high level of air pollution. In summary, the sky appears blue because of the way light interacts with the tiny molecules of gases in the air, known as Rayleigh scattering. This phenomenon scatters shorter wavelengths of light, such as blue and violet, more than longer wavelengths, giving the sky its characteristic blue color. embedding: base_url='http://localhost:11434' model='llama2' embed_instruction='passage: ' query_instruction='query: ' mirostat=None mirostat_eta=None mirostat_tau=None num_ctx=None num_gpu=None num_thread=None repeat_last_n=None repeat_penalty=None temperature=None stop=None tfs_z=None top_k=None top_p=None model_kwargs=None Traceback (most recent call last): File "olama.py", line 23, in <module> vectorstore = Chroma.from_documents(documents=all_splits, embedding=oembed) File "./Env/chatbot/lib/python3.8/site-packages/langchain/vectorstores/chroma.py", line 771, in from_documents return cls.from_texts( File "./Env/chatbot/lib/python3.8/site-packages/langchain/vectorstores/chroma.py", line 729, in from_texts chroma_collection.add_texts( File "./Env/chatbot/lib/python3.8/site-packages/langchain/vectorstores/chroma.py", line 275, in add_texts embeddings = self._embedding_function.embed_documents(texts) File "./Env/chatbot/lib/python3.8/site-packages/langchain/embeddings/ollama.py", line 190, in embed_documents embeddings = self._embed(instruction_pairs) File "./Env/chatbot/lib/python3.8/site-packages/langchain/embeddings/ollama.py", line 175, in _embed embeddings = self._process_emb_response(prompt) File "./Env/chatbot/lib/python3.8/site-packages/langchain/embeddings/ollama.py", line 160, in _process_emb_response raise ValueError( ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"} ``` And even i try to get embeddings via api ```terminal curl -X POST http://localhost:11434/api/embeddings -d '{ "model": "llama2", "prompt": "hello, how are you?" }' ``` My embeddings looks like this: ```terminal {"embedding":[0.713813066482544,-1.8217487335205078,0.48764699697494507,-0.8590573668479919,-0.7165888547897339,0.09285138547420502,-0.06305933743715286,0.8703135251998901,-0.7629101872444153,0.40360304713249207,1.6491974592208862,-0.7351164817810059,0.9032987356185913,1.0884538888931274,0.754738986492157,-0.0351458303630352,-0.2696535289287567,0.030562296509742737,-0.5470462441444397,-0.7511221170425415,1.6396052837371826,-2.254915714263916,-0.2600090503692627,-2.861804723739624,-0.31693896651268005,-1.0240172147750854,-0.7449401617050171,-2.3529539108276367,1.3769773244857788,-0.15259328484535217,1.564031958580017,0.33758652210235596,-1.2046291828155518,2.713618040084839,-0.22524534165859222,0.08619225025177002,0.5370852947235107,1.7855254411697388,-0.06518085300922394,-0.0628420040011406,0.5781055092811584,-4.234992504119873,-1.2907594442367554,-0.1936117261648178,1.3087000846862793,0.14808768033981323,-1.689073085784912,-3.103379011154175,0.5116130709648132,-1.674410104751587,0.026191502809524536,0.31160175800323486,1.843047022819519,-0.754763662815094,2.64321231842041,-0.9525578618049622,1.4135092496871948,1.014215350151062,1.701998233795166,0.35821205377578735,-4.310467720031738,1.3969742059707642,-0.3026293218135834,1.1710561513900757,-3.1511785984039307,-0.9500783681869507,0.25463706254959106,0.2536858320236206,0.2566526234149933,-0.8113981485366821,1.434630274772644,-0.41049930453300476,1.3408557176589966,0.3780902028083801,-2.971435546875,1.556931495666504,2.2950439453125,-2.0468714237213135,-1.6436930894851685,-0.6824514269828796,0.2970106601715088,0.48574963212013245,1.3311458826065063,-1.2823209762573242,-1.0872153043746948,1.0507322549819946,1.6134350299835205,0.44947174191474915,0.14205259084701538,-1.4551608562469482,-0.43960702419281006,-1.6097815036773682,-3.165051221847534,0.6144835352897644,1.2260065078735352,0.8544708490371704,-0.5544838905334473,-1.207687258720398,0.3186914324760437,-0.9924833178520203,0.48585525155067444,-0.987743616104126,-1.0047131776809692... ```
GiteaMirror added the questionbug labels 2026-04-28 03:38:56 -05:00
GiteaMirror commented 2026-04-28 03:39:02 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Dec 19, 2023):

Hi @doganaktarr, is there any error captured in the ollama server logs? Here's where you can find them on your OS:
https://github.com/jmorganca/ollama/blob/main/docs/faq.md#how-can-i-view-the-logs

<!-- gh-comment-id:1863324103 --> @BruceMacD commented on GitHub (Dec 19, 2023): Hi @doganaktarr, is there any error captured in the ollama server logs? Here's where you can find them on your OS: https://github.com/jmorganca/ollama/blob/main/docs/faq.md#how-can-i-view-the-logs
GiteaMirror commented 2026-04-28 03:39:05 -05:00
Author
Owner
Copy Link

@vipinap98 commented on GitHub (Feb 14, 2024):

Is this issue solved? I'm still having the same issue!

<!-- gh-comment-id:1943161674 --> @vipinap98 commented on GitHub (Feb 14, 2024): Is this issue solved? I'm still having the same issue!
GiteaMirror commented 2026-04-28 03:39:05 -05:00
Author
Owner
Copy Link

@jerryola1 commented on GitHub (Feb 26, 2024):

I had this same error, and how I fixed it was using WSL for windows and creating a virtual environment.

<!-- gh-comment-id:1964324451 --> @jerryola1 commented on GitHub (Feb 26, 2024): I had this same error, and how I fixed it was using WSL for windows and creating a virtual environment.
GiteaMirror commented 2026-04-28 03:39:05 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Mar 11, 2024):

@doganaktarr @jerryola1 @vipinap98, may I ask if any of you are still running into the problem?

This issue was created before we added official embedding support on Ollama -- and it means it'll inference only on the CPU back then. I'm wondering if it's hitting some bottleneck there. Now, it's GPU accelerated.

<!-- gh-comment-id:1989170393 --> @mchiang0610 commented on GitHub (Mar 11, 2024): @doganaktarr @jerryola1 @vipinap98, may I ask if any of you are still running into the problem? This issue was created before we added official embedding support on Ollama -- and it means it'll inference only on the CPU back then. I'm wondering if it's hitting some bottleneck there. Now, it's GPU accelerated.
GiteaMirror commented 2026-04-28 03:39:06 -05:00
Author
Owner
Copy Link

@jerryola1 commented on GitHub (Mar 11, 2024):

No, it's fixed from my end

<!-- gh-comment-id:1989179528 --> @jerryola1 commented on GitHub (Mar 11, 2024): No, it's fixed from my end
GiteaMirror commented 2026-04-28 03:39:06 -05:00
Author
Owner
Copy Link

@edchengmooree commented on GitHub (Mar 12, 2024):

New user here but I still get this issue on my end, ollama serve showing constant 500 errors on latest version

`[GIN] 2024/03/12 - 11:26:01 | 200 | 12.865901039s | 127.0.0.1 | POST "/api/pull"

[GIN] 2024/03/12 - 11:26:04 | 500 | 296.28µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:26:04 | 500 | 227.67µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:26:05 | 500 | 280.857µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:26:07 | 500 | 310.478µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:26:13 | 500 | 320.161µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:26:27 | 500 | 322.997µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:26:48 | 500 | 306.062µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:27:33 | 500 | 311.024µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:27:33 | 500 | 260.77µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:27:35 | 500 | 267.115µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:27:37 | 500 | 301.359µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:27:43 | 500 | 311.964µs | 127.0.0.1 | POST "/api/embeddings"

[GIN] 2024/03/12 - 11:27:55 | 500 | 301.202µs | 127.0.0.1 | POST "/api/embeddings"
`

<!-- gh-comment-id:1991441742 --> @edchengmooree commented on GitHub (Mar 12, 2024): New user here but I still get this issue on my end, ollama serve showing constant 500 errors on latest version `[GIN] 2024/03/12 - 11:26:01 | 200 | 12.865901039s | 127.0.0.1 | POST "/api/pull" [GIN] 2024/03/12 - 11:26:04 | 500 | 296.28µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:26:04 | 500 | 227.67µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:26:05 | 500 | 280.857µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:26:07 | 500 | 310.478µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:26:13 | 500 | 320.161µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:26:27 | 500 | 322.997µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:26:48 | 500 | 306.062µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:27:33 | 500 | 311.024µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:27:33 | 500 | 260.77µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:27:35 | 500 | 267.115µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:27:37 | 500 | 301.359µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:27:43 | 500 | 311.964µs | 127.0.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 11:27:55 | 500 | 301.202µs | 127.0.0.1 | POST "/api/embeddings" `
GiteaMirror commented 2026-04-28 03:39:07 -05:00
Author
Owner
Copy Link

@SikamikanikoBG commented on GitHub (Mar 12, 2024):

I had the same issue with .27 version. Today I upgraded to .28 and I have the same:

Flowise:
image

And the server logs:
[GIN] 2024/03/12 - 10:47:07 | 500 | 507.948µs | 172.17.0.1 | POST "/api/embeddings"
[GIN] 2024/03/12 - 10:47:26 | 500 | 505.182µs | 172.17.0.1 | POST "/api/embeddings"
[GIN] 2024/03/12 - 10:47:26 | 500 | 702.412µs | 172.17.0.1 | POST "/api/embeddings"
[GIN] 2024/03/12 - 10:47:28 | 500 | 428.304µs | 172.17.0.1 | POST "/api/embeddings"
[GIN] 2024/03/12 - 10:47:30 | 500 | 632.877µs | 172.17.0.1 | POST "/api/embeddings"
[GIN] 2024/03/12 - 10:47:36 | 500 | 531.406µs | 172.17.0.1 | POST "/api/embeddings"
[GIN] 2024/03/12 - 10:47:44 | 500 | 560.034µs | 172.17.0.1 | POST "/api/embeddings"
[GIN] 2024/03/12 - 10:47:44 | 500 | 389.676µs | 172.17.0.1 | POST "/api/embeddings"
[GIN] 2024/03/12 - 10:47:44 | 500 | 807.651µs | 172.17.0.1 | POST "/api/embeddings"
[GIN] 2024/03/12 - 10:47:45 | 500 | 477.732µs | 172.17.0.1 | POST "/api/embeddings"

<!-- gh-comment-id:1991511787 --> @SikamikanikoBG commented on GitHub (Mar 12, 2024): I had the same issue with .27 version. Today I upgraded to .28 and I have the same: Flowise: ![image](https://github.com/ollama/ollama/assets/46193504/69732924-9108-4132-a562-8075b41f73ed) And the server logs: [GIN] 2024/03/12 - 10:47:07 | 500 | 507.948µs | 172.17.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 10:47:26 | 500 | 505.182µs | 172.17.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 10:47:26 | 500 | 702.412µs | 172.17.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 10:47:28 | 500 | 428.304µs | 172.17.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 10:47:30 | 500 | 632.877µs | 172.17.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 10:47:36 | 500 | 531.406µs | 172.17.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 10:47:44 | 500 | 560.034µs | 172.17.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 10:47:44 | 500 | 389.676µs | 172.17.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 10:47:44 | 500 | 807.651µs | 172.17.0.1 | POST "/api/embeddings" [GIN] 2024/03/12 - 10:47:45 | 500 | 477.732µs | 172.17.0.1 | POST "/api/embeddings"
GiteaMirror commented 2026-04-28 03:39:07 -05:00
Author
Owner
Copy Link

@doanaktar commented on GitHub (Mar 13, 2024):

@doganaktarr @jerryola1 @vipinap98, may I ask if any of you are still running into the problem?

This issue was created before we added official embedding support on Ollama -- and it means it'll inference only on the CPU back then. I'm wondering if it's hitting some bottleneck there. Now, it's GPU accelerated.

When i try the same code on version 0.1.26 i don't get any error.

<!-- gh-comment-id:1993709030 --> @doanaktar commented on GitHub (Mar 13, 2024): > @doganaktarr @jerryola1 @vipinap98, may I ask if any of you are still running into the problem? > > This issue was created before we added official embedding support on Ollama -- and it means it'll inference only on the CPU back then. I'm wondering if it's hitting some bottleneck there. Now, it's GPU accelerated. When i try the same code on version 0.1.26 i don't get any error.
GiteaMirror commented 2026-04-28 03:39:07 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 7, 2024):

Hi folks this should be fixed now - please let me know if that's not the case

<!-- gh-comment-id:2097124760 --> @jmorganca commented on GitHub (May 7, 2024): Hi folks this should be fixed now - please let me know if that's not the case
GiteaMirror commented 2026-04-28 03:39:08 -05:00
Author
Owner
Copy Link

@uzumakinaruto19 commented on GitHub (May 23, 2024):

ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"}

still I'm getting with the latest ollama docker

Hi folks this should be fixed now - please let me know if that's not the case

@jmorganca

only with the llama/ollama:0.1.32 version it works,
doesn't work with 0.1.28,37 and latest(as far as I checked)
Randomly it works, but most of the time fails

@mchiang0610, do you have any idea how to fix this?

<!-- gh-comment-id:2126700878 --> @uzumakinaruto19 commented on GitHub (May 23, 2024): ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"} still I'm getting with the latest ollama docker > Hi folks this should be fixed now - please let me know if that's not the case @jmorganca only with the llama/ollama:0.1.32 version it works, doesn't work with 0.1.28,37 and latest(as far as I checked) Randomly it works, but most of the time fails @mchiang0610, do you have any idea how to fix this?
GiteaMirror commented 2026-04-28 03:39:08 -05:00
Author
Owner
Copy Link

@emmanuel-torres1 commented on GitHub (Jun 30, 2024):

I have the same issue and I am running Ollama locally:

ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"}

<!-- gh-comment-id:2198638355 --> @emmanuel-torres1 commented on GitHub (Jun 30, 2024): I have the same issue and I am running Ollama locally: ValueError: Error raised by inference API HTTP code: 500, {"error":"failed to generate embedding"}
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 question
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#47378
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?