github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #2353] sentiment analysis works interactively, but it doesn't via API #63403

New Issue
Closed
opened 2026-05-03 13:21:19 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-03 13:21:19 -05:00
Owner
Copy Link

Originally created by @Blu-Eagle on GitHub (Feb 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2353

Originally assigned to: @bmizerany on GitHub.

when I use LLAMA2 asking for a sentiment analysis of a text, it works, while if I try to do the same using the API I do not get the same result, just a sort of summary of the text.

the code I use for the api is the following:

`
url = "http://localhost:11434/api/generate"

payload = {
"model": "llama2",
"prompt": prompt,
"system": comando,
"stream": False
}
payload_json = json.dumps(payload)
headers = {"Content-Type": "application/json"}
response = requests.post(url, data=payload_json, headers=headers)
`
where
prompt: is the text
comando: is the request: "Make the sentiment analysis of the text provided"

the same request and the same text are given interactively and only interactively I get a sentiment analysis.
I use LLAMA2 7B.

thanks for any suggestions.
Giuseppe

Originally created by @Blu-Eagle on GitHub (Feb 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2353 Originally assigned to: @bmizerany on GitHub. when I use LLAMA2 asking for a sentiment analysis of a text, it works, while if I try to do the same using the API I do not get the same result, just a sort of summary of the text. the code I use for the api is the following: ` url = "http://localhost:11434/api/generate" payload = { "model": "llama2", "prompt": prompt, "system": comando, "stream": False } payload_json = json.dumps(payload) headers = {"Content-Type": "application/json"} response = requests.post(url, data=payload_json, headers=headers) ` where prompt: is the text comando: is the request: "Make the sentiment analysis of the text provided" the same request and the same text are given interactively and only interactively I get a sentiment analysis. I use LLAMA2 7B. thanks for any suggestions. Giuseppe
GiteaMirror added the needs more info label 2026-05-03 13:21:19 -05:00
GiteaMirror commented 2026-05-03 13:21:24 -05:00
Author
Owner
Copy Link

@ahsan123322 commented on GitHub (Feb 5, 2024):

are you using custom API?

<!-- gh-comment-id:1926289988 --> @ahsan123322 commented on GitHub (Feb 5, 2024): are you using custom API?
GiteaMirror commented 2026-05-03 13:21:25 -05:00
Author
Owner
Copy Link

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

@Blu-Eagle llama2 is a general purpose model so it will likely respond with some length hard to parse response. Have you tried tuning your prompt, temperature, tokens expected, etc to coerce it into responding more tersely?

<!-- gh-comment-id:1989681884 --> @bmizerany commented on GitHub (Mar 12, 2024): @Blu-Eagle llama2 is a general purpose model so it will likely respond with some length hard to parse response. Have you tried tuning your prompt, temperature, tokens expected, etc to coerce it into responding more tersely?
GiteaMirror commented 2026-05-03 13:21:26 -05:00
Author
Owner
Copy Link

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

Closing for now. Please reopen with a complete code example and environment information (including ollama version) if the issue persists.

<!-- gh-comment-id:1992552047 --> @bmizerany commented on GitHub (Mar 12, 2024): Closing for now. Please reopen with a complete code example and environment information (including ollama version) if the issue persists.
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 needs more info
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#63403
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?