[GH-ISSUE #1170] Allow LLMs to Query a Database Directly #62631

New Issue

GiteaMirror · 2026-05-03T09:50:24-05:00

GiteaMirror commented

2026-05-03 09:50:24 -05:00

Originally created by @FaizelK on GitHub (Nov 17, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1170

I have installed ollama and can run prompts, example: ollama run llama2 "why is the sky blue?"

Is there any way to connect to MYSQL database and start asking about database data, example:
`###### database file######
database.cnf
host="localhost"
user="admin"
passsword="admin"
database="mDatabase"

ollama run llama2 database "how many users are administrators?"

I have searched repository and I cannot see anything like this, I also went to langchain docs but did not see an example with ollama

`

Originally created by @FaizelK on GitHub (Nov 17, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1170 I have installed ollama and can run prompts, example: `ollama run llama2 "why is the sky blue?"` Is there any way to connect to MYSQL database and start asking about database data, example: `###### database file###### database.cnf host="localhost" user="admin" passsword="admin" database="mDatabase" ollama run llama2 database "how many users are administrators?" I have searched repository and I cannot see anything like this, I also went to langchain docs but did not see an example with ollama `

GiteaMirror added the feature request label 2026-05-03 09:50:24 -05:00

GiteaMirror closed this issue

2026-05-03 09:50:25 -05:00

GiteaMirror commented

2026-05-03 09:50:27 -05:00

@BruceMacD commented on GitHub (Nov 17, 2023):

Hi @FaizelK this is not built into Ollama, but it is a good example of a workflow that you could build on top of Ollama. As an aside I would recommend dumping the contents of the database to a file which you parse into structured data and feed into Ollama rather than giving the LLM direct access to query your database.

@BruceMacD commented on GitHub (Nov 17, 2023): Hi @FaizelK this is not built into Ollama, but it is a good example of a workflow that you could build on top of Ollama. As an aside I would recommend dumping the contents of the database to a file which you parse into structured data and feed into Ollama rather than giving the LLM direct access to query your database.

GiteaMirror commented

2026-05-03 09:50:28 -05:00

@FaizelK commented on GitHub (Nov 18, 2023):

@BruceMacD i would think access directly to database is better than exporting data into a file, can you imagine a database with millions of records? also langchain and openai have this plugin (database agents) I am working on this so it can work with ollama. if you create a database user with only read access/privilege then it is no harm.

@FaizelK commented on GitHub (Nov 18, 2023): @BruceMacD i would think access directly to database is better than exporting data into a file, can you imagine a database with millions of records? also langchain and openai have this plugin (database agents) I am working on this so it can work with ollama. if you create a database user with only read access/privilege then it is no harm.

GiteaMirror commented

2026-05-03 09:50:29 -05:00

@MostlyKIGuess commented on GitHub (Nov 18, 2023):

Hi @FaizelK this is not built into Ollama, but it is a good example of a workflow that you could build on top of Ollama. As an aside I would recommend dumping the contents of the database to a file which you parse into structured data and feed into Ollama rather than giving the LLM direct access to query your database.

How exactly could someone do this?

@MostlyKIGuess commented on GitHub (Nov 18, 2023): > Hi @FaizelK this is not built into Ollama, but it is a good example of a workflow that you could build on top of Ollama. As an aside I would recommend dumping the contents of the database to a file which you parse into structured data and feed into Ollama rather than giving the LLM direct access to query your database. How exactly could someone do this?

GiteaMirror commented

2026-05-03 09:50:29 -05:00

@igorschlum commented on GitHub (Nov 21, 2023):

Hello @FaizelK,

Direct database connections are not currently supported by Ollama. However, you can create a webpage that connects to the database and extracts data from it, which can then be analyzed by Ollama using the following link:

https://ollama.ai/blog/building-llm-powered-web-apps

@igorschlum commented on GitHub (Nov 21, 2023): Hello @FaizelK, Direct database connections are not currently supported by Ollama. However, you can create a webpage that connects to the database and extracts data from it, which can then be analyzed by Ollama using the following link: https://ollama.ai/blog/building-llm-powered-web-apps

GiteaMirror commented

2026-05-03 09:50:30 -05:00

@UnexpectedMaker commented on GitHub (Jan 30, 2024):

I'm also looking for a way to use OLLAMA with a local SQLITE database - The reason this is important is contents of a database can change, a little, or a lot, by so many external factors, and I want the query of the data in the database to be on the current data in there.

Converting the data into a file format for ingesting into a vector store means that the data is now static and instantly out of date.

I also want the system to be able to not just query the data but to also alter the data as required. Think about a stock management system, where you can ask how many of product XX is in stock, and also reduce the quantity when needed etc

All langchain examples I've seen so far require the use of OpenAI - and I'd like this to be 100% local and not via a hosted website for data querying.

@UnexpectedMaker commented on GitHub (Jan 30, 2024): I'm also looking for a way to use OLLAMA with a local SQLITE database - The reason this is important is contents of a database can change, a little, or a lot, by so many external factors, and I want the query of the data in the database to be on the current data in there. Converting the data into a file format for ingesting into a vector store means that the data is now static and instantly out of date. I also want the system to be able to not just query the data but to also alter the data as required. Think about a stock management system, where you can ask how many of product XX is in stock, and also reduce the quantity when needed etc All langchain examples I've seen so far require the use of OpenAI - and I'd like this to be 100% local and not via a hosted website for data querying.

GiteaMirror commented

2026-05-03 09:50:31 -05:00

@easp commented on GitHub (Jan 30, 2024):

@UnexpectedMaker You found the Github. Did you check out the examples folder in the repo?

There are multiple Langchain examples using Ollama. The ones I checked use a local option for generating embeddings.

Also make sure you check out SQLite-VSS support in Langchain.

@easp commented on GitHub (Jan 30, 2024): @UnexpectedMaker You found the Github. Did you check out the examples folder in the repo? There are multiple Langchain examples using Ollama. The ones I checked use a local option for generating embeddings. Also make sure you check out SQLite-VSS support in Langchain.

GiteaMirror commented

2026-05-03 09:50:32 -05:00

@UnexpectedMaker commented on GitHub (Jan 30, 2024):

@UnexpectedMaker You found the Github. Did you check out the examples folder in the repo?

There are multiple Langchain examples using Ollama. The ones I checked use a local option for generating embeddings.

Also make sure you check out SQLite-VSS support in Langchain.

I found the GitHub - I checked the examples. None deal with or show how to do ollama + local model + langchain (or llamaIndex) to actually access a standard SQL database (not as a vector source, 100% was NOT what I asked for) and query it to return results.

I dont want to ingest documents and store the quantized vector data in an SQL database - I want the model to look into a normal SQL database and have it strain itself on the structure - and then be able to pull results out of the tables.

Every example I can find online (google, blogs, YouTube) show this only working with llama.cpp + (llamaindex/langchain) and openai.

Rather than asking me to check the examples - if you think there's an actual example in there that does what I have asked about, and what the OP asked about, please point specifically to that example.

Thanks :)

@UnexpectedMaker commented on GitHub (Jan 30, 2024): > @UnexpectedMaker You found the Github. Did you check out the examples folder in the repo? > > There are multiple Langchain examples using Ollama. The ones I checked use a local option for generating embeddings. > > Also make sure you check out SQLite-VSS support in Langchain. I found the GitHub - I checked the examples. None deal with or show how to do ollama + local model + langchain (or llamaIndex) to actually access a standard SQL database (not as a vector source, 100% was NOT what I asked for) and query it to return results. I dont want to ingest documents and store the quantized vector data in an SQL database - I want the model to look into a normal SQL database and have it strain itself on the structure - and then be able to pull results out of the tables. Every example I can find online (google, blogs, YouTube) show this only working with llama.cpp + (llamaindex/langchain) and openai. Rather than asking me to check the examples - if you think there's an actual example in there that does what I have asked about, and what the OP asked about, please point specifically to that example. Thanks :)

GiteaMirror commented

2026-05-03 09:50:33 -05:00

@FaizelK commented on GitHub (Feb 20, 2024):

I am back, back with gifts, sweets and all the good stuff.
Yes, I have found an open source solution to my original question. I will add my reference if i get 10 hearts on this solution
After 100's of hours ...... Here it goes........
@BruceMacD
@MostlyKIGuess

from langchain_community.chat_models import ChatOllama
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.llms import Ollama
from langchain_community.utilities import SQLDatabase
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough

# Define chat models
llama2_chat = ChatOllama(model="llama2:13b-chat")  # Change model if required
llama2_code = ChatOllama(model="codellama:7b-instruct")

# Set model (choose one of the following options)
llm = llama2_chat  # Option 1
# llm = Ollama(model="llama2:13b-chat", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))  # Option 2

# Connect to database
db = SQLDatabase.from_uri("mysql+pymysql://database_user:password@localhost/databasName")

# Define functions for schema retrieval and query execution
def get_schema(_):
    return db.get_table_info()

def run_query(query):
    return db.run(query)

# Create prompt templates
template1 = """
Based on the table schema below, write a SQL query that would answer the user's question:
{schema}

Question: {question}
SQL Query:
"""
prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "Given an input question, convert it to a SQL query. No pre-amble."),
        ("human", template1),
    ]
)

template2 = """
Based on the table schema below, question, sql query, and sql response, write a natural language response:
{schema}

Question: {question}
SQL Query: {query}
SQL Response: {response}
"""
prompt_response = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "Given an input question and SQL response, convert it to a natural language answer. No pre-amble.",
        ),
        ("human", template2),
    ]
)

# Construct chains for query generation and response
sql_response = (
    RunnablePassthrough.assign(schema=get_schema)
    | prompt
    | llm.bind(stop=["\nSQLResult:"])
    | StrOutputParser()
)

full_chain = (
    RunnablePassthrough.assign(query=sql_response)
    | RunnablePassthrough.assign(
        schema=get_schema,
        response=lambda x: db.run(x["query"]),
    )
    | prompt_response
    | llm
)

# Invoke the full chain and print the final response
TheFinalResponse = full_chain.invoke({"question": ThePrompt})
print(TheFinalResponse)

@FaizelK commented on GitHub (Feb 20, 2024): I am back, back with gifts, sweets and all the good stuff. Yes, I have found an open source solution to my original question. I will add my reference if i get 10 hearts on this solution After 100's of hours ...... Here it goes........ @BruceMacD @MostlyKIGuess ``` from langchain_community.chat_models import ChatOllama from langchain.callbacks.manager import CallbackManager from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler from langchain.llms import Ollama from langchain_community.utilities import SQLDatabase from langchain_core.prompts import ChatPromptTemplate from langchain_core.output_parsers import StrOutputParser from langchain_core.runnables import RunnablePassthrough # Define chat models llama2_chat = ChatOllama(model="llama2:13b-chat") # Change model if required llama2_code = ChatOllama(model="codellama:7b-instruct") # Set model (choose one of the following options) llm = llama2_chat # Option 1 # llm = Ollama(model="llama2:13b-chat", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])) # Option 2 # Connect to database db = SQLDatabase.from_uri("mysql+pymysql://database_user:password@localhost/databasName") # Define functions for schema retrieval and query execution def get_schema(_): return db.get_table_info() def run_query(query): return db.run(query) # Create prompt templates template1 = """ Based on the table schema below, write a SQL query that would answer the user's question: {schema} Question: {question} SQL Query: """ prompt = ChatPromptTemplate.from_messages( [ ("system", "Given an input question, convert it to a SQL query. No pre-amble."), ("human", template1), ] ) template2 = """ Based on the table schema below, question, sql query, and sql response, write a natural language response: {schema} Question: {question} SQL Query: {query} SQL Response: {response} """ prompt_response = ChatPromptTemplate.from_messages( [ ( "system", "Given an input question and SQL response, convert it to a natural language answer. No pre-amble.", ), ("human", template2), ] ) # Construct chains for query generation and response sql_response = ( RunnablePassthrough.assign(schema=get_schema) | prompt | llm.bind(stop=["\nSQLResult:"]) | StrOutputParser() ) full_chain = ( RunnablePassthrough.assign(query=sql_response) | RunnablePassthrough.assign( schema=get_schema, response=lambda x: db.run(x["query"]), ) | prompt_response | llm ) # Invoke the full chain and print the final response TheFinalResponse = full_chain.invoke({"question": ThePrompt}) print(TheFinalResponse) ```

GiteaMirror commented

2026-05-03 09:50:35 -05:00

@igorschlum commented on GitHub (Feb 20, 2024):

Nice.

I understand that the user describes their query in natural language. It's converted into SQL queries by an LLM. The script retrieves results from a database. Then, another LLM transforms those results into an easy-to-understand response for the user.

@igorschlum commented on GitHub (Feb 20, 2024): Nice. I understand that the user describes their query in natural language. It's converted into SQL queries by an LLM. The script retrieves results from a database. Then, another LLM transforms those results into an easy-to-understand response for the user.

GiteaMirror commented

2026-05-03 09:50:37 -05:00

@FaizelK commented on GitHub (Feb 21, 2024):

Yes,
The users prompt could be

User prompt
"how many users are admins?" or "how many users in total?"

first LLM
translates this user promp to sql "select count(*) from table"

second LLM
translates the sql results into english and final response is
"there are 10 users in total"

@FaizelK commented on GitHub (Feb 21, 2024): Yes, The users prompt could be User prompt "how many users are admins?" or "how many users in total?" first LLM translates this user promp to sql "select count(*) from table" second LLM translates the sql results into english and final response is "there are 10 users in total"

GiteaMirror commented

2026-05-03 09:50:38 -05:00

@FaizelK commented on GitHub (Feb 21, 2024):

Does anyone know how to become a contributor? i would like to add this module as part of this repo

@FaizelK commented on GitHub (Feb 21, 2024): Does anyone know how to become a contributor? i would like to add this module as part of this repo

GiteaMirror commented

2026-05-03 09:50:38 -05:00

@luckydonald commented on GitHub (Feb 23, 2024):

@FaizelK you can always fork the repository, copying it into your account, work on it, and in the end submit a pull request to this repository, which can then be merged into the code here.

It's not garantieed to be merged, but people can also come to your fork in that case and use that instead.

@luckydonald commented on GitHub (Feb 23, 2024): @FaizelK you can always **fork** the repository, copying it into your account, work on it, and in the end submit a **pull request** to this repository, which can then be merged into the code here. It's not garantieed to be merged, but people can also come to your fork in that case and use that instead.

GiteaMirror commented

2026-05-03 09:50:39 -05:00

@monjurulkarim commented on GitHub (Feb 24, 2024):

I am back, back with gifts, sweets and all the good stuff. Yes, I have found an open source solution to my original question. I will add my reference if i get 10 hearts on this solution After 100's of hours ...... Here it goes........ @BruceMacD @MostlyKIGuess

from langchain_community.chat_models import ChatOllama
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.llms import Ollama
from langchain_community.utilities import SQLDatabase
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough

# Define chat models
llama2_chat = ChatOllama(model="llama2:13b-chat")  # Change model if required
llama2_code = ChatOllama(model="codellama:7b-instruct")

# Set model (choose one of the following options)
llm = llama2_chat  # Option 1
# llm = Ollama(model="llama2:13b-chat", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))  # Option 2

# Connect to database
db = SQLDatabase.from_uri("mysql+pymysql://database_user:password@localhost/databasName")

# Define functions for schema retrieval and query execution
def get_schema(_):
    return db.get_table_info()

def run_query(query):
    return db.run(query)

# Create prompt templates
template1 = """
Based on the table schema below, write a SQL query that would answer the user's question:
{schema}

Question: {question}
SQL Query:
"""
prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "Given an input question, convert it to a SQL query. No pre-amble."),
        ("human", template1),
    ]
)

template2 = """
Based on the table schema below, question, sql query, and sql response, write a natural language response:
{schema}

Question: {question}
SQL Query: {query}
SQL Response: {response}
"""
prompt_response = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "Given an input question and SQL response, convert it to a natural language answer. No pre-amble.",
        ),
        ("human", template2),
    ]
)

# Construct chains for query generation and response
sql_response = (
    RunnablePassthrough.assign(schema=get_schema)
    | prompt
    | llm.bind(stop=["\nSQLResult:"])
    | StrOutputParser()
)

full_chain = (
    RunnablePassthrough.assign(query=sql_response)
    | RunnablePassthrough.assign(
        schema=get_schema,
        response=lambda x: db.run(x["query"]),
    )
    | prompt_response
    | llm
)

# Invoke the full chain and print the final response
TheFinalResponse = full_chain.invoke({"question": ThePrompt})
print(TheFinalResponse)

@FaizelK Could you please share the original reference?

@monjurulkarim commented on GitHub (Feb 24, 2024): > I am back, back with gifts, sweets and all the good stuff. Yes, I have found an open source solution to my original question. I will add my reference if i get 10 hearts on this solution After 100's of hours ...... Here it goes........ @BruceMacD @MostlyKIGuess > > ``` > from langchain_community.chat_models import ChatOllama > from langchain.callbacks.manager import CallbackManager > from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler > from langchain.llms import Ollama > from langchain_community.utilities import SQLDatabase > from langchain_core.prompts import ChatPromptTemplate > from langchain_core.output_parsers import StrOutputParser > from langchain_core.runnables import RunnablePassthrough > > # Define chat models > llama2_chat = ChatOllama(model="llama2:13b-chat") # Change model if required > llama2_code = ChatOllama(model="codellama:7b-instruct") > > # Set model (choose one of the following options) > llm = llama2_chat # Option 1 > # llm = Ollama(model="llama2:13b-chat", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])) # Option 2 > > # Connect to database > db = SQLDatabase.from_uri("mysql+pymysql://database_user:password@localhost/databasName") > > # Define functions for schema retrieval and query execution > def get_schema(_): > return db.get_table_info() > > def run_query(query): > return db.run(query) > > # Create prompt templates > template1 = """ > Based on the table schema below, write a SQL query that would answer the user's question: > {schema} > > Question: {question} > SQL Query: > """ > prompt = ChatPromptTemplate.from_messages( > [ > ("system", "Given an input question, convert it to a SQL query. No pre-amble."), > ("human", template1), > ] > ) > > template2 = """ > Based on the table schema below, question, sql query, and sql response, write a natural language response: > {schema} > > Question: {question} > SQL Query: {query} > SQL Response: {response} > """ > prompt_response = ChatPromptTemplate.from_messages( > [ > ( > "system", > "Given an input question and SQL response, convert it to a natural language answer. No pre-amble.", > ), > ("human", template2), > ] > ) > > # Construct chains for query generation and response > sql_response = ( > RunnablePassthrough.assign(schema=get_schema) > | prompt > | llm.bind(stop=["\nSQLResult:"]) > | StrOutputParser() > ) > > full_chain = ( > RunnablePassthrough.assign(query=sql_response) > | RunnablePassthrough.assign( > schema=get_schema, > response=lambda x: db.run(x["query"]), > ) > | prompt_response > | llm > ) > > # Invoke the full chain and print the final response > TheFinalResponse = full_chain.invoke({"question": ThePrompt}) > print(TheFinalResponse) > ``` @FaizelK Could you please share the original reference?

GiteaMirror commented

2026-05-03 09:50:39 -05:00

@monjurulkarim commented on GitHub (Feb 28, 2024):

@igorschlum I think here is the source: https://github.com/langchain-ai/langchain/blob/master/cookbook/LLaMA2_sql_chat.ipynb

@monjurulkarim commented on GitHub (Feb 28, 2024): @igorschlum I think here is the source: https://github.com/langchain-ai/langchain/blob/master/cookbook/LLaMA2_sql_chat.ipynb

GiteaMirror commented

2026-05-03 09:50:39 -05:00

@FaizelK commented on GitHub (Feb 28, 2024):

Yep, that is the source

@FaizelK commented on GitHub (Feb 28, 2024): Yep, that is the source

GiteaMirror commented

2026-05-03 09:50:40 -05:00

@FaizelK commented on GitHub (May 3, 2024):

hi @BruceMacD have you managed to implement this feature yet?

@FaizelK commented on GitHub (May 3, 2024): hi @BruceMacD have you managed to implement this feature yet?

GiteaMirror commented

2026-05-03 09:50:40 -05:00

@BruceMacD commented on GitHub (May 3, 2024):

@FaizelK this probably isn't a feature we would build into Ollama directly, but people have built tools around this use-case now.

I haven't used this yet, but Vanna looks interesting:
https://vanna.ai/docs/other-database-ollama-chromadb/

@BruceMacD commented on GitHub (May 3, 2024): @FaizelK this probably isn't a feature we would build into Ollama directly, but people have built tools around this use-case now. I haven't used this yet, but Vanna looks interesting: https://vanna.ai/docs/other-database-ollama-chromadb/

GiteaMirror commented

2026-05-03 09:50:41 -05:00

@jmorganca commented on GitHub (May 9, 2024):

Thanks for the issue! Yes I will close this for

#834
#3880

@jmorganca commented on GitHub (May 9, 2024): Thanks for the issue! Yes I will close this for #834 #3880

GiteaMirror commented

2026-05-03 09:50:43 -05:00

@xhinodread commented on GitHub (Sep 1, 2024):

Hi, that is super, but, how can by than in javascript
I don t can
saludos

@xhinodread commented on GitHub (Sep 1, 2024): Hi, that is super, but, how can by than in javascript I don t can saludos

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

parth-launch-plan-gating

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#62631