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 #10008] Request for Help: Checking My ollama - Python - Based Embed Code #6560

New Issue
Closed
opened 2026-04-12 18:11:18 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 18:11:18 -05:00
Owner
Copy Link

Originally created by @20246688 on GitHub (Mar 27, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10008

import asyncio
from ollama import AsyncClient
import chromadb

documents = [
"Llamas are members of the camelid family meaning they're pretty closely related to vicuñas and camels",
"Llamas were first domesticated and used as pack animals 4,000 to 5,000 years ago in the Peruvian highlands",
"Llamas can grow as much as 6 feet tall though the average llama between 5 feet 6 inches and 5 feet 9 inches tall",
"Llamas weigh between 280 and 450 pounds and can carry 25 to 30 percent of their body weight",
"Llamas are vegetarians and have very efficient digestive systems",
"Llamas live to be about 20 years old, though some only live for 15 years and others live to be 30 years old",
]

client = chromadb.Client()
collection = client.create_collection(name="docs")

async def store_embeddings(ollama_client):
model_name = 'granite-embedding:278m'
for i, doc in enumerate(documents):
try:
response = await ollama_client.embed(model=model_name, input=doc)
embeddings = response.get("embeddings", [])
if embeddings:
collection.add(
ids=[str(i)],
embeddings=embeddings,
documents=[doc]
)
else:
print(f"Failed to store document {i}: Empty embedding vector")
except Exception as e:
print(f"Failed to store document {i}: {e}")

async def query_embedding(ollama_client, query_text):
model_name = 'granite-embedding:278m'
try:
response = await ollama_client.embed(model=model_name, input=query_text)
embeddings = response.get("embeddings", [])
if not embeddings:
print("Query failed: Empty embedding vector")
return "No matching content found"

    if isinstance(embeddings, list) and len(embeddings) == 1 and isinstance(embeddings[0], list):
        embeddings = embeddings[0]

    results = collection.query(query_embeddings=embeddings, n_results=1)
    return results['documents'][0][0] if results['documents'] else "No matching content found"
except Exception as e:
    print(f"Query failed: {e}")
    return "Query failed"

async def main():
ollama_client = AsyncClient(host='XXX')
await store_embeddings(ollama_client)

query_text = "What animals are llamas related to?"
result = await query_embedding(ollama_client, query_text)
print(f"Result: {result}")

if name == "main":
asyncio.run(main())

Hello! I wrote a Python program based on the embed demo in ollama-Python. But I found the results weren't ideal. Could you please help me check if there's anything wrong with the code?

Originally created by @20246688 on GitHub (Mar 27, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10008 import asyncio from ollama import AsyncClient import chromadb documents = [ "Llamas are members of the camelid family meaning they're pretty closely related to vicuñas and camels", "Llamas were first domesticated and used as pack animals 4,000 to 5,000 years ago in the Peruvian highlands", "Llamas can grow as much as 6 feet tall though the average llama between 5 feet 6 inches and 5 feet 9 inches tall", "Llamas weigh between 280 and 450 pounds and can carry 25 to 30 percent of their body weight", "Llamas are vegetarians and have very efficient digestive systems", "Llamas live to be about 20 years old, though some only live for 15 years and others live to be 30 years old", ] client = chromadb.Client() collection = client.create_collection(name="docs") async def store_embeddings(ollama_client): model_name = 'granite-embedding:278m' for i, doc in enumerate(documents): try: response = await ollama_client.embed(model=model_name, input=doc) embeddings = response.get("embeddings", []) if embeddings: collection.add( ids=[str(i)], embeddings=embeddings, documents=[doc] ) else: print(f"Failed to store document {i}: Empty embedding vector") except Exception as e: print(f"Failed to store document {i}: {e}") async def query_embedding(ollama_client, query_text): model_name = 'granite-embedding:278m' try: response = await ollama_client.embed(model=model_name, input=query_text) embeddings = response.get("embeddings", []) if not embeddings: print("Query failed: Empty embedding vector") return "No matching content found" if isinstance(embeddings, list) and len(embeddings) == 1 and isinstance(embeddings[0], list): embeddings = embeddings[0] results = collection.query(query_embeddings=embeddings, n_results=1) return results['documents'][0][0] if results['documents'] else "No matching content found" except Exception as e: print(f"Query failed: {e}") return "Query failed" async def main(): ollama_client = AsyncClient(host='XXX') await store_embeddings(ollama_client) query_text = "What animals are llamas related to?" result = await query_embedding(ollama_client, query_text) print(f"Result: {result}") if __name__ == "__main__": asyncio.run(main()) Hello! I wrote a Python program based on the embed demo in ollama-Python. But I found the results weren't ideal. Could you please help me check if there's anything wrong with the code?
GiteaMirror added the question label 2026-04-12 18:11:18 -05:00
GiteaMirror commented 2026-04-12 18:11:19 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 27, 2025):

What's not ideal? Please wrap the code in a markdown block (```python ... ```).

<!-- gh-comment-id:2756968237 --> @rick-github commented on GitHub (Mar 27, 2025): What's not ideal? Please wrap the code in a markdown block (\`\`\`python ... \`\`\`).
GiteaMirror commented 2026-04-12 18:11:20 -05:00
Author
Owner
Copy Link

@20246688 commented on GitHub (Mar 27, 2025):

import asyncio
from ollama import AsyncClient
import chromadb

documents = [
    "Llamas are members of the camelid family meaning they're pretty closely related to vicuñas and camels",
    "Llamas were first domesticated and used as pack animals 4,000 to 5,000 years ago in the Peruvian highlands",
    "Llamas can grow as much as 6 feet tall though the average llama between 5 feet 6 inches and 5 feet 9 inches tall",
    "Llamas weigh between 280 and 450 pounds and can carry 25 to 30 percent of their body weight",
    "Llamas are vegetarians and have very efficient digestive systems",
    "Llamas live to be about 20 years old, though some only live for 15 years and others live to be 30 years old",
]

client = chromadb.Client()
collection = client.create_collection(name="docs")


async def store_embeddings(ollama_client):
    model_name = 'granite-embedding:278m'
    for i, doc in enumerate(documents):
        try:
            response = await ollama_client.embed(model=model_name, input=doc)
            embeddings = response.get("embeddings", [])
            if embeddings:
                collection.add(
                    ids=[str(i)],
                    embeddings=embeddings,
                    documents=[doc]
                )
            else:
                print(f"Failed to store document {i}: Empty embedding vector")
        except Exception as e:
            print(f"Failed to store document {i}: {e}")


async def query_embedding(ollama_client, query_text):
    model_name = 'granite-embedding:278m'
    try:
        response = await ollama_client.embed(model=model_name, input=query_text)
        embeddings = response.get("embeddings", [])
        if not embeddings:
            print("Query failed: Empty embedding vector")
            return "No matching content found"

        if isinstance(embeddings, list) and len(embeddings) == 1 and isinstance(embeddings[0], list):
            embeddings = embeddings[0]

        results = collection.query(query_embeddings=embeddings, n_results=1)
        return results['documents'][0][0] if results['documents'] else "No matching content found"
    except Exception as e:
        print(f"Query failed: {e}")
        return "Query failed"


async def main():
    ollama_client = AsyncClient(host='XXX')
    await store_embeddings(ollama_client)

    query_text = "What animals are llamas related to?"
    result = await query_embedding(ollama_client, query_text)
    print(f"Result: {result}")


if __name__ == "__main__":
    asyncio.run(main())

I'm really sorry. I'm not familiar with this. Is it like this?I mainly want to ask if this code is written correctly. Can it make the vectors be generated correctly and used for proper matching? I referred to the code on this website: https://ollama.com/blog/embedding-models.

<!-- gh-comment-id:2757002828 --> @20246688 commented on GitHub (Mar 27, 2025): ```python import asyncio from ollama import AsyncClient import chromadb documents = [ "Llamas are members of the camelid family meaning they're pretty closely related to vicuñas and camels", "Llamas were first domesticated and used as pack animals 4,000 to 5,000 years ago in the Peruvian highlands", "Llamas can grow as much as 6 feet tall though the average llama between 5 feet 6 inches and 5 feet 9 inches tall", "Llamas weigh between 280 and 450 pounds and can carry 25 to 30 percent of their body weight", "Llamas are vegetarians and have very efficient digestive systems", "Llamas live to be about 20 years old, though some only live for 15 years and others live to be 30 years old", ] client = chromadb.Client() collection = client.create_collection(name="docs") async def store_embeddings(ollama_client): model_name = 'granite-embedding:278m' for i, doc in enumerate(documents): try: response = await ollama_client.embed(model=model_name, input=doc) embeddings = response.get("embeddings", []) if embeddings: collection.add( ids=[str(i)], embeddings=embeddings, documents=[doc] ) else: print(f"Failed to store document {i}: Empty embedding vector") except Exception as e: print(f"Failed to store document {i}: {e}") async def query_embedding(ollama_client, query_text): model_name = 'granite-embedding:278m' try: response = await ollama_client.embed(model=model_name, input=query_text) embeddings = response.get("embeddings", []) if not embeddings: print("Query failed: Empty embedding vector") return "No matching content found" if isinstance(embeddings, list) and len(embeddings) == 1 and isinstance(embeddings[0], list): embeddings = embeddings[0] results = collection.query(query_embeddings=embeddings, n_results=1) return results['documents'][0][0] if results['documents'] else "No matching content found" except Exception as e: print(f"Query failed: {e}") return "Query failed" async def main(): ollama_client = AsyncClient(host='XXX') await store_embeddings(ollama_client) query_text = "What animals are llamas related to?" result = await query_embedding(ollama_client, query_text) print(f"Result: {result}") if __name__ == "__main__": asyncio.run(main()) ``` I'm really sorry. I'm not familiar with this. Is it like this?I mainly want to ask if this code is written correctly. Can it make the vectors be generated correctly and used for proper matching? I referred to the code on this website: https://ollama.com/blog/embedding-models.
GiteaMirror commented 2026-04-12 18:11:20 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 27, 2025):

Yes, it generates vectors and they are used to return appropriate results.

<!-- gh-comment-id:2757814839 --> @rick-github commented on GitHub (Mar 27, 2025): Yes, it generates vectors and they are used to return appropriate results.
GiteaMirror commented 2026-04-12 18:11:21 -05:00
Author
Owner
Copy Link

@20246688 commented on GitHub (Mar 28, 2025):

是的，它会生成向量，并用于返回适当的结果。

Thanks for your approval! I'll keep trying to improve it.

<!-- gh-comment-id:2760000194 --> @20246688 commented on GitHub (Mar 28, 2025): > 是的，它会生成向量，并用于返回适当的结果。 Thanks for your approval! I'll keep trying to improve it.
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 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#6560
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?