add all ollama

ollama/docs/tutorials/langchainjs.md

+# Using LangChain with Ollama using JavaScript
+
+In this tutorial, we are going to use JavaScript with LangChain and Ollama to learn about something just a touch more recent. In August 2023, there was a series of wildfires on Maui. There is no way an LLM trained before that time can know about this, since their training data would not include anything as recent as that. So we can find the [Wikipedia article about the fires](https://en.wikipedia.org/wiki/2023_Hawaii_wildfires) and ask questions about the contents.
+
+To get started, let's just use **LangChain** to ask a simple question to a model. To do this with JavaScript, we need to install **LangChain**:
+
+```bash
+npm install @langchain/community
+```
+
+Now we can start building out our JavaScript:
+
+```javascript
+import { Ollama } from "@langchain/community/llms/ollama";
+
+const ollama = new Ollama({
+  baseUrl: "http://localhost:11434",
+  model: "llama3.1",
+});
+
+const answer = await ollama.invoke(`why is the sky blue?`);
+
+console.log(answer);
+```
+
+That will get us the same thing as if we ran `ollama run llama3.1 "why is the sky blue"` in the terminal. But we want to load a document from the web to ask a question against. **Cheerio** is a great library for ingesting a webpage, and **LangChain** uses it in their **CheerioWebBaseLoader**. So let's install **Cheerio** and build that part of the app.
+
+```bash
+npm install cheerio
+```
+
+```javascript
+import { CheerioWebBaseLoader } from "langchain/document_loaders/web/cheerio";
+
+const loader = new CheerioWebBaseLoader("https://en.wikipedia.org/wiki/2023_Hawaii_wildfires");
+const data = await loader.load();
+```
+
+That will load the document. Although this page is smaller than the Odyssey, it is certainly bigger than the context size for most LLMs. So we are going to need to split into smaller pieces, and then select just the pieces relevant to our question. This is a great use for a vector datastore. In this example, we will use the **MemoryVectorStore** that is part of **LangChain**. But there is one more thing we need to get the content into the datastore. We have to run an embeddings process that converts the tokens in the text into a series of vectors. And for that, we are going to use **Tensorflow**. There is a lot of stuff going on in this one. First, install the **Tensorflow** components that we need.
+
+```javascript
+npm install @tensorflow/tfjs-core@3.6.0 @tensorflow/tfjs-converter@3.6.0 @tensorflow-models/universal-sentence-encoder@1.3.3 @tensorflow/tfjs-node@4.10.0
+```
+
+If you just install those components without the version numbers, it will install the latest versions, but there are conflicts within **Tensorflow**, so you need to install the compatible versions.
+
+```javascript
+import { RecursiveCharacterTextSplitter } from "langchain/text_splitter"
+import { MemoryVectorStore } from "langchain/vectorstores/memory";
+import "@tensorflow/tfjs-node";
+import { TensorFlowEmbeddings } from "langchain/embeddings/tensorflow";
+
+// Split the text into 500 character chunks. And overlap each chunk by 20 characters
+const textSplitter = new RecursiveCharacterTextSplitter({
+ chunkSize: 500,
+ chunkOverlap: 20
+});
+const splitDocs = await textSplitter.splitDocuments(data);
+
+// Then use the TensorFlow Embedding to store these chunks in the datastore
+const vectorStore = await MemoryVectorStore.fromDocuments(splitDocs, new TensorFlowEmbeddings());
+```
+
+To connect the datastore to a question asked to a LLM, we need to use the concept at the heart of **LangChain**: the chain. Chains are a way to connect a number of activities together to accomplish a particular tasks. There are a number of chain types available, but for this tutorial we are using the **RetrievalQAChain**.
+
+```javascript
+import { RetrievalQAChain } from "langchain/chains";
+
+const retriever = vectorStore.asRetriever();
+const chain = RetrievalQAChain.fromLLM(ollama, retriever);
+const result = await chain.call({query: "When was Hawaii's request for a major disaster declaration approved?"});
+console.log(result.text)
+```
+
+So we created a retriever, which is a way to return the chunks that match a query from a datastore. And then connect the retriever and the model via a chain. Finally, we send a query to the chain, which results in an answer using our document as a source. The answer it returned was correct, August 10, 2023.
+
+And that is a simple introduction to what you can do with **LangChain** and **Ollama.**

ollama/docs/tutorials/langchainpy.md

+# Using LangChain with Ollama in Python
+
+Let's imagine we are studying the classics, such as **the Odyssey** by **Homer**. We might have a question about Neleus and his family. If you ask llama2 for that info, you may get something like:
+
+> I apologize, but I'm a large language model, I cannot provide information on individuals or families that do not exist in reality. Neleus is not a real person or character, and therefore does not have a family or any other personal details. My apologies for any confusion. Is there anything else I can help you with?
+
+This sounds like a typical censored response, but even llama2-uncensored gives a mediocre answer:
+
+> Neleus was a legendary king of Pylos and the father of Nestor, one of the Argonauts. His mother was Clymene, a sea nymph, while his father was Neptune, the god of the sea.
+
+So let's figure out how we can use **LangChain** with Ollama to ask our question to the actual document, the Odyssey by Homer, using Python.
+
+Let's start by asking a simple question that we can get an answer to from the **Llama2** model using **Ollama**. First, we need to install the **LangChain** package:
+
+`pip install langchain_community`
+
+Then we can create a model and ask the question:
+
+```python
+from langchain_community.llms import Ollama
+ollama = Ollama(
+    base_url='http://localhost:11434',
+    model="llama3"
+)
+print(ollama.invoke("why is the sky blue"))
+```
+
+Notice that we are defining the model and the base URL for Ollama.
+
+Now let's load a document to ask questions against. I'll load up the Odyssey by Homer, which you can find at Project Gutenberg. We will need **WebBaseLoader** which is part of **LangChain** and loads text from any webpage. On my machine, I also needed to install **bs4** to get that to work, so run `pip install bs4`.
+
+```python
+from langchain.document_loaders import WebBaseLoader
+loader = WebBaseLoader("https://www.gutenberg.org/files/1727/1727-h/1727-h.htm")
+data = loader.load()
+```
+
+This file is pretty big. Just the preface is 3000 tokens. Which means the full document won't fit into the context for the model. So we need to split it up into smaller pieces.
+
+```python
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+text_splitter=RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
+all_splits = text_splitter.split_documents(data)
+```
+
+It's split up, but we have to find the relevant splits and then submit those to the model. We can do this by creating embeddings and storing them in a vector database. We can use Ollama directly to instantiate an embedding model. We will use ChromaDB in this example for a vector database. `pip install chromadb`
+We also need to pull embedding model: `ollama pull nomic-embed-text`
+```python
+from langchain.embeddings import OllamaEmbeddings
+from langchain.vectorstores import Chroma
+oembed = OllamaEmbeddings(base_url="http://localhost:11434", model="nomic-embed-text")
+vectorstore = Chroma.from_documents(documents=all_splits, embedding=oembed)
+```
+
+Now let's ask a question from the document. **Who was Neleus, and who is in his family?** Neleus is a character in the Odyssey, and the answer can be found in our text.
+
+```python
+question="Who is Neleus and who is in Neleus' family?"
+docs = vectorstore.similarity_search(question)
+len(docs)
+```
+
+This will output the number of matches for chunks of data similar to the search.
+
+The next thing is to send the question and the relevant parts of the docs to the model to see if we can get a good answer. But we are stitching two parts of the process together, and that is called a chain. This means we need to define a chain:
+
+```python
+from langchain.chains import RetrievalQA
+qachain=RetrievalQA.from_chain_type(ollama, retriever=vectorstore.as_retriever())
+res = qachain.invoke({"query": question})
+print(res['result'])
+```
+
+The answer received from this chain was:
+
+> Neleus is a character in Homer's "Odyssey" and is mentioned in the context of Penelope's suitors. Neleus is the father of Chloris, who is married to Neleus and bears him several children, including Nestor, Chromius, Periclymenus, and Pero. Amphinomus, the son of Nisus, is also mentioned as a suitor of Penelope and is known for his good natural disposition and agreeable conversation.
+
+It's not a perfect answer, as it implies Neleus married his daughter when actually Chloris "was the youngest daughter to Amphion son of Iasus and king of Minyan Orchomenus, and was Queen in Pylos".
+
+I updated the chunk_overlap for the text splitter to 20 and tried again and got a much better answer:
+
+> Neleus is a character in Homer's epic poem "The Odyssey." He is the husband of Chloris, who is the youngest daughter of Amphion son of Iasus and king of Minyan Orchomenus. Neleus has several children with Chloris, including Nestor, Chromius, Periclymenus, and Pero.
+
+And that is a much better answer.

ollama/docs/tutorials/nvidia-jetson.md

+# Running Ollama on NVIDIA Jetson Devices
+
+Ollama runs well on [NVIDIA Jetson Devices](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/) and should run out of the box with the standard installation instructions. 
+
+The following has been tested on [JetPack 5.1.2](https://developer.nvidia.com/embedded/jetpack), but should also work on JetPack 6.0.
+
+- Install Ollama via standard Linux command (ignore the 404 error): `curl https://ollama.com/install.sh | sh`
+- Pull the model you want to use (e.g. mistral): `ollama pull mistral`
+- Start an interactive session: `ollama run mistral`
+
+And that's it!
+
+# Running Ollama in Docker
+
+When running GPU accelerated applications in Docker, it is highly recommended to use [dusty-nv jetson-containers repo](https://github.com/dusty-nv/jetson-containers).
\ No newline at end of file

ollama/docs/windows.md

+# Ollama Windows Preview
+
+Welcome to the Ollama Windows preview.
+
+No more WSL required!
+
+Ollama now runs as a native Windows application, including NVIDIA and AMD Radeon GPU support.
+After installing Ollama Windows Preview, Ollama will run in the background and
+the `ollama` command line is available in `cmd`, `powershell` or your favorite
+terminal application. As usual the Ollama [api](./api.md) will be served on
+`http://localhost:11434`.
+
+As this is a preview release, you should expect a few bugs here and there.  If
+you run into a problem you can reach out on
+[Discord](https://discord.gg/ollama), or file an
+[issue](https://github.com/ollama/ollama/issues).
+Logs will often be helpful in diagnosing the problem (see
+[Troubleshooting](#troubleshooting) below)
+
+## System Requirements
+
+* Windows 10 22H2 or newer, Home or Pro
+* NVIDIA 452.39 or newer Drivers if you have an NVIDIA card
+* AMD Radeon Driver https://www.amd.com/en/support if you have a Radeon card
+
+Ollama uses unicode characters for progress indication, which may render as unknown squares in some older terminal fonts in Windows 10. If you see this, try changing your terminal font settings.
+
+## API Access
+
+Here's a quick example showing API access from `powershell`
+```powershell
+(Invoke-WebRequest -method POST -Body '{"model":"llama3", "prompt":"Why is the sky blue?", "stream": false}' -uri http://localhost:11434/api/generate ).Content | ConvertFrom-json
+```
+
+## Troubleshooting
+
+While we're in preview, `OLLAMA_DEBUG` is always enabled, which adds
+a "view logs" menu item to the app, and increases logging for the GUI app and
+server.
+
+Ollama on Windows stores files in a few different locations.  You can view them in
+the explorer window by hitting `<cmd>+R` and type in:
+- `explorer %LOCALAPPDATA%\Ollama` contains logs, and downloaded updates
+    - *app.log* contains most resent logs from the GUI application
+    - *server.log* contains the most recent server logs
+    - *upgrade.log* contains log output for upgrades
+- `explorer %LOCALAPPDATA%\Programs\Ollama` contains the binaries (The installer adds this to your user PATH)
+- `explorer %HOMEPATH%\.ollama` contains models and configuration
+- `explorer %TEMP%` contains temporary executable files in one or more `ollama*` directories
+
+
+## Standalone CLI
+
+The easiest way to install Ollama on Windows is to use the `OllamaSetup.exe`
+installer. It installs in your account without requiring Administrator rights.
+We update Ollama regularly to support the latest models, and this installer will
+help you keep up to date.
+
+If you'd like to install or integrate Ollama as a service, a standalone
+`ollama-windows-amd64.zip` zip file is available containing only the Ollama CLI
+and GPU library dependencies for Nvidia and AMD. This allows for embedding
+Ollama in existing applications, or running it as a system service via `ollama
+serve` with tools such as [NSSM](https://nssm.cc/).

ollama/envconfig/config.go

+package envconfig
+
+import (
+	"fmt"
+	"log/slog"
+	"math"
+	"net"
+	"net/url"
+	"os"
+	"path/filepath"
+	"runtime"
+	"strconv"
+	"strings"
+	"time"
+)
+
+// Host returns the scheme and host. Host can be configured via the OLLAMA_HOST environment variable.
+// Default is scheme "http" and host "127.0.0.1:11434"
+func Host() *url.URL {
+	defaultPort := "11434"
+
+	s := strings.TrimSpace(Var("OLLAMA_HOST"))
+	scheme, hostport, ok := strings.Cut(s, "://")
+	switch {
+	case !ok:
+		scheme, hostport = "http", s
+	case scheme == "http":
+		defaultPort = "80"
+	case scheme == "https":
+		defaultPort = "443"
+	}
+
+	// trim trailing slashes
+	hostport = strings.TrimRight(hostport, "/")
+
+	host, port, err := net.SplitHostPort(hostport)
+	if err != nil {
+		host, port = "127.0.0.1", defaultPort
+		if ip := net.ParseIP(strings.Trim(hostport, "[]")); ip != nil {
+			host = ip.String()
+		} else if hostport != "" {
+			host = hostport
+		}
+	}
+
+	if n, err := strconv.ParseInt(port, 10, 32); err != nil || n > 65535 || n < 0 {
+		slog.Warn("invalid port, using default", "port", port, "default", defaultPort)
+		return &url.URL{
+			Scheme: scheme,
+			Host:   net.JoinHostPort(host, defaultPort),
+		}
+	}
+
+	return &url.URL{
+		Scheme: scheme,
+		Host:   net.JoinHostPort(host, port),
+	}
+}
+
+// Origins returns a list of allowed origins. Origins can be configured via the OLLAMA_ORIGINS environment variable.
+func Origins() (origins []string) {
+	if s := Var("OLLAMA_ORIGINS"); s != "" {
+		origins = strings.Split(s, ",")
+	}
+
+	for _, origin := range []string{"localhost", "127.0.0.1", "0.0.0.0"} {
+		origins = append(origins,
+			fmt.Sprintf("http://%s", origin),
+			fmt.Sprintf("https://%s", origin),
+			fmt.Sprintf("http://%s", net.JoinHostPort(origin, "*")),
+			fmt.Sprintf("https://%s", net.JoinHostPort(origin, "*")),
+		)
+	}
+
+	origins = append(origins,
+		"app://*",
+		"file://*",
+		"tauri://*",
+	)
+
+	return origins
+}
+
+// Models returns the path to the models directory. Models directory can be configured via the OLLAMA_MODELS environment variable.
+// Default is $HOME/.ollama/models
+func Models() string {
+	if s := Var("OLLAMA_MODELS"); s != "" {
+		return s
+	}
+
+	home, err := os.UserHomeDir()
+	if err != nil {
+		panic(err)
+	}
+
+	return filepath.Join(home, ".ollama", "models")
+}
+
+// KeepAlive returns the duration that models stay loaded in memory. KeepAlive can be configured via the OLLAMA_KEEP_ALIVE environment variable.
+// Negative values are treated as infinite. Zero is treated as no keep alive.
+// Default is 5 minutes.
+func KeepAlive() (keepAlive time.Duration) {
+	keepAlive = 5 * time.Minute
+	if s := Var("OLLAMA_KEEP_ALIVE"); s != "" {
+		if d, err := time.ParseDuration(s); err == nil {
+			keepAlive = d
+		} else if n, err := strconv.ParseInt(s, 10, 64); err == nil {
+			keepAlive = time.Duration(n) * time.Second
+		}
+	}
+
+	if keepAlive < 0 {
+		return time.Duration(math.MaxInt64)
+	}
+
+	return keepAlive
+}
+
+func Bool(k string) func() bool {
+	return func() bool {
+		if s := Var(k); s != "" {
+			b, err := strconv.ParseBool(s)
+			if err != nil {
+				return true
+			}
+
+			return b
+		}
+
+		return false
+	}
+}
+
+var (
+	// Debug enabled additional debug information.
+	Debug = Bool("OLLAMA_DEBUG")
+	// FlashAttention enables the experimental flash attention feature.
+	FlashAttention = Bool("OLLAMA_FLASH_ATTENTION")
+	// NoHistory disables readline history.
+	NoHistory = Bool("OLLAMA_NOHISTORY")
+	// NoPrune disables pruning of model blobs on startup.
+	NoPrune = Bool("OLLAMA_NOPRUNE")
+	// SchedSpread allows scheduling models across all GPUs.
+	SchedSpread = Bool("OLLAMA_SCHED_SPREAD")
+	// IntelGPU enables experimental Intel GPU detection.
+	IntelGPU = Bool("OLLAMA_INTEL_GPU")
+)
+
+func String(s string) func() string {
+	return func() string {
+		return Var(s)
+	}
+}
+
+var (
+	LLMLibrary = String("OLLAMA_LLM_LIBRARY")
+	TmpDir     = String("OLLAMA_TMPDIR")
+
+	CudaVisibleDevices    = String("CUDA_VISIBLE_DEVICES")
+	HipVisibleDevices     = String("HIP_VISIBLE_DEVICES")
+	RocrVisibleDevices    = String("ROCR_VISIBLE_DEVICES")
+	GpuDeviceOrdinal      = String("GPU_DEVICE_ORDINAL")
+	HsaOverrideGfxVersion = String("HSA_OVERRIDE_GFX_VERSION")
+)
+
+func RunnersDir() (p string) {
+	if p := Var("OLLAMA_RUNNERS_DIR"); p != "" {
+		return p
+	}
+
+	if runtime.GOOS != "windows" {
+		return
+	}
+
+	defer func() {
+		if p == "" {
+			slog.Error("unable to locate llm runner directory. Set OLLAMA_RUNNERS_DIR to the location of 'ollama_runners'")
+		}
+	}()
+
+	// On Windows we do not carry the payloads inside the main executable
+	exe, err := os.Executable()
+	if err != nil {
+		return
+	}
+
+	cwd, err := os.Getwd()
+	if err != nil {
+		return
+	}
+
+	var paths []string
+	for _, root := range []string{filepath.Dir(exe), cwd} {
+		paths = append(paths,
+			root,
+			filepath.Join(root, "windows-"+runtime.GOARCH),
+			filepath.Join(root, "dist", "windows-"+runtime.GOARCH),
+		)
+	}
+
+	// Try a few variations to improve developer experience when building from source in the local tree
+	for _, path := range paths {
+		candidate := filepath.Join(path, "ollama_runners")
+		if _, err := os.Stat(candidate); err == nil {
+			p = candidate
+			break
+		}
+	}
+
+	return p
+}
+
+func Uint(key string, defaultValue uint) func() uint {
+	return func() uint {
+		if s := Var(key); s != "" {
+			if n, err := strconv.ParseUint(s, 10, 64); err != nil {
+				slog.Warn("invalid environment variable, using default", "key", key, "value", s, "default", defaultValue)
+			} else {
+				return uint(n)
+			}
+		}
+
+		return defaultValue
+	}
+}
+
+var (
+	// NumParallel sets the number of parallel model requests. NumParallel can be configured via the OLLAMA_NUM_PARALLEL environment variable.
+	NumParallel = Uint("OLLAMA_NUM_PARALLEL", 0)
+	// MaxRunners sets the maximum number of loaded models. MaxRunners can be configured via the OLLAMA_MAX_LOADED_MODELS environment variable.
+	MaxRunners = Uint("OLLAMA_MAX_LOADED_MODELS", 0)
+	// MaxQueue sets the maximum number of queued requests. MaxQueue can be configured via the OLLAMA_MAX_QUEUE environment variable.
+	MaxQueue = Uint("OLLAMA_MAX_QUEUE", 512)
+	// MaxVRAM sets a maximum VRAM override in bytes. MaxVRAM can be configured via the OLLAMA_MAX_VRAM environment variable.
+	MaxVRAM = Uint("OLLAMA_MAX_VRAM", 0)
+)
+
+type EnvVar struct {
+	Name        string
+	Value       any
+	Description string
+}
+
+func AsMap() map[string]EnvVar {
+	ret := map[string]EnvVar{
+		"OLLAMA_DEBUG":             {"OLLAMA_DEBUG", Debug(), "Show additional debug information (e.g. OLLAMA_DEBUG=1)"},
+		"OLLAMA_FLASH_ATTENTION":   {"OLLAMA_FLASH_ATTENTION", FlashAttention(), "Enabled flash attention"},
+		"OLLAMA_HOST":              {"OLLAMA_HOST", Host(), "IP Address for the ollama server (default 127.0.0.1:11434)"},
+		"OLLAMA_KEEP_ALIVE":        {"OLLAMA_KEEP_ALIVE", KeepAlive(), "The duration that models stay loaded in memory (default \"5m\")"},
+		"OLLAMA_LLM_LIBRARY":       {"OLLAMA_LLM_LIBRARY", LLMLibrary(), "Set LLM library to bypass autodetection"},
+		"OLLAMA_MAX_LOADED_MODELS": {"OLLAMA_MAX_LOADED_MODELS", MaxRunners(), "Maximum number of loaded models per GPU"},
+		"OLLAMA_MAX_QUEUE":         {"OLLAMA_MAX_QUEUE", MaxQueue(), "Maximum number of queued requests"},
+		"OLLAMA_MODELS":            {"OLLAMA_MODELS", Models(), "The path to the models directory"},
+		"OLLAMA_NOHISTORY":         {"OLLAMA_NOHISTORY", NoHistory(), "Do not preserve readline history"},
+		"OLLAMA_NOPRUNE":           {"OLLAMA_NOPRUNE", NoPrune(), "Do not prune model blobs on startup"},
+		"OLLAMA_NUM_PARALLEL":      {"OLLAMA_NUM_PARALLEL", NumParallel(), "Maximum number of parallel requests"},
+		"OLLAMA_ORIGINS":           {"OLLAMA_ORIGINS", Origins(), "A comma separated list of allowed origins"},
+		"OLLAMA_RUNNERS_DIR":       {"OLLAMA_RUNNERS_DIR", RunnersDir(), "Location for runners"},
+		"OLLAMA_SCHED_SPREAD":      {"OLLAMA_SCHED_SPREAD", SchedSpread(), "Always schedule model across all GPUs"},
+		"OLLAMA_TMPDIR":            {"OLLAMA_TMPDIR", TmpDir(), "Location for temporary files"},
+	}
+	if runtime.GOOS != "darwin" {
+		ret["CUDA_VISIBLE_DEVICES"] = EnvVar{"CUDA_VISIBLE_DEVICES", CudaVisibleDevices(), "Set which NVIDIA devices are visible"}
+		ret["HIP_VISIBLE_DEVICES"] = EnvVar{"HIP_VISIBLE_DEVICES", HipVisibleDevices(), "Set which AMD devices are visible"}
+		ret["ROCR_VISIBLE_DEVICES"] = EnvVar{"ROCR_VISIBLE_DEVICES", RocrVisibleDevices(), "Set which AMD devices are visible"}
+		ret["GPU_DEVICE_ORDINAL"] = EnvVar{"GPU_DEVICE_ORDINAL", GpuDeviceOrdinal(), "Set which AMD devices are visible"}
+		ret["HSA_OVERRIDE_GFX_VERSION"] = EnvVar{"HSA_OVERRIDE_GFX_VERSION", HsaOverrideGfxVersion(), "Override the gfx used for all detected AMD GPUs"}
+		ret["OLLAMA_INTEL_GPU"] = EnvVar{"OLLAMA_INTEL_GPU", IntelGPU(), "Enable experimental Intel GPU detection"}
+	}
+	return ret
+}
+
+func Values() map[string]string {
+	vals := make(map[string]string)
+	for k, v := range AsMap() {
+		vals[k] = fmt.Sprintf("%v", v.Value)
+	}
+	return vals
+}
+
+// Var returns an environment variable stripped of leading and trailing quotes or spaces
+func Var(key string) string {
+	return strings.Trim(strings.TrimSpace(os.Getenv(key)), "\"'")
+}

ollama/envconfig/config_test.go

+package envconfig
+
+import (
+	"math"
+	"testing"
+	"time"
+
+	"github.com/google/go-cmp/cmp"
+)
+
+func TestHost(t *testing.T) {
+	cases := map[string]struct {
+		value  string
+		expect string
+	}{
+		"empty":               {"", "127.0.0.1:11434"},
+		"only address":        {"1.2.3.4", "1.2.3.4:11434"},
+		"only port":           {":1234", ":1234"},
+		"address and port":    {"1.2.3.4:1234", "1.2.3.4:1234"},
+		"hostname":            {"example.com", "example.com:11434"},
+		"hostname and port":   {"example.com:1234", "example.com:1234"},
+		"zero port":           {":0", ":0"},
+		"too large port":      {":66000", ":11434"},
+		"too small port":      {":-1", ":11434"},
+		"ipv6 localhost":      {"[::1]", "[::1]:11434"},
+		"ipv6 world open":     {"[::]", "[::]:11434"},
+		"ipv6 no brackets":    {"::1", "[::1]:11434"},
+		"ipv6 + port":         {"[::1]:1337", "[::1]:1337"},
+		"extra space":         {" 1.2.3.4 ", "1.2.3.4:11434"},
+		"extra quotes":        {"\"1.2.3.4\"", "1.2.3.4:11434"},
+		"extra space+quotes":  {" \" 1.2.3.4 \" ", "1.2.3.4:11434"},
+		"extra single quotes": {"'1.2.3.4'", "1.2.3.4:11434"},
+		"http":                {"http://1.2.3.4", "1.2.3.4:80"},
+		"http port":           {"http://1.2.3.4:4321", "1.2.3.4:4321"},
+		"https":               {"https://1.2.3.4", "1.2.3.4:443"},
+		"https port":          {"https://1.2.3.4:4321", "1.2.3.4:4321"},
+	}
+
+	for name, tt := range cases {
+		t.Run(name, func(t *testing.T) {
+			t.Setenv("OLLAMA_HOST", tt.value)
+			if host := Host(); host.Host != tt.expect {
+				t.Errorf("%s: expected %s, got %s", name, tt.expect, host.Host)
+			}
+		})
+	}
+}
+
+func TestOrigins(t *testing.T) {
+	cases := []struct {
+		value  string
+		expect []string
+	}{
+		{"", []string{
+			"http://localhost",
+			"https://localhost",
+			"http://localhost:*",
+			"https://localhost:*",
+			"http://127.0.0.1",
+			"https://127.0.0.1",
+			"http://127.0.0.1:*",
+			"https://127.0.0.1:*",
+			"http://0.0.0.0",
+			"https://0.0.0.0",
+			"http://0.0.0.0:*",
+			"https://0.0.0.0:*",
+			"app://*",
+			"file://*",
+			"tauri://*",
+		}},
+		{"http://10.0.0.1", []string{
+			"http://10.0.0.1",
+			"http://localhost",
+			"https://localhost",
+			"http://localhost:*",
+			"https://localhost:*",
+			"http://127.0.0.1",
+			"https://127.0.0.1",
+			"http://127.0.0.1:*",
+			"https://127.0.0.1:*",
+			"http://0.0.0.0",
+			"https://0.0.0.0",
+			"http://0.0.0.0:*",
+			"https://0.0.0.0:*",
+			"app://*",
+			"file://*",
+			"tauri://*",
+		}},
+		{"http://172.16.0.1,https://192.168.0.1", []string{
+			"http://172.16.0.1",
+			"https://192.168.0.1",
+			"http://localhost",
+			"https://localhost",
+			"http://localhost:*",
+			"https://localhost:*",
+			"http://127.0.0.1",
+			"https://127.0.0.1",
+			"http://127.0.0.1:*",
+			"https://127.0.0.1:*",
+			"http://0.0.0.0",
+			"https://0.0.0.0",
+			"http://0.0.0.0:*",
+			"https://0.0.0.0:*",
+			"app://*",
+			"file://*",
+			"tauri://*",
+		}},
+		{"http://totally.safe,http://definitely.legit", []string{
+			"http://totally.safe",
+			"http://definitely.legit",
+			"http://localhost",
+			"https://localhost",
+			"http://localhost:*",
+			"https://localhost:*",
+			"http://127.0.0.1",
+			"https://127.0.0.1",
+			"http://127.0.0.1:*",
+			"https://127.0.0.1:*",
+			"http://0.0.0.0",
+			"https://0.0.0.0",
+			"http://0.0.0.0:*",
+			"https://0.0.0.0:*",
+			"app://*",
+			"file://*",
+			"tauri://*",
+		}},
+	}
+	for _, tt := range cases {
+		t.Run(tt.value, func(t *testing.T) {
+			t.Setenv("OLLAMA_ORIGINS", tt.value)
+
+			if diff := cmp.Diff(Origins(), tt.expect); diff != "" {
+				t.Errorf("%s: mismatch (-want +got):\n%s", tt.value, diff)
+			}
+		})
+	}
+}
+
+func TestBool(t *testing.T) {
+	cases := map[string]bool{
+		"":      false,
+		"true":  true,
+		"false": false,
+		"1":     true,
+		"0":     false,
+		// invalid values
+		"random":    true,
+		"something": true,
+	}
+
+	for k, v := range cases {
+		t.Run(k, func(t *testing.T) {
+			t.Setenv("OLLAMA_BOOL", k)
+			if b := Bool("OLLAMA_BOOL")(); b != v {
+				t.Errorf("%s: expected %t, got %t", k, v, b)
+			}
+		})
+	}
+}
+
+func TestUint(t *testing.T) {
+	cases := map[string]uint{
+		"0":    0,
+		"1":    1,
+		"1337": 1337,
+		// default values
+		"":       11434,
+		"-1":     11434,
+		"0o10":   11434,
+		"0x10":   11434,
+		"string": 11434,
+	}
+
+	for k, v := range cases {
+		t.Run(k, func(t *testing.T) {
+			t.Setenv("OLLAMA_UINT", k)
+			if i := Uint("OLLAMA_UINT", 11434)(); i != v {
+				t.Errorf("%s: expected %d, got %d", k, v, i)
+			}
+		})
+	}
+}
+
+func TestKeepAlive(t *testing.T) {
+	cases := map[string]time.Duration{
+		"":       5 * time.Minute,
+		"1s":     time.Second,
+		"1m":     time.Minute,
+		"1h":     time.Hour,
+		"5m0s":   5 * time.Minute,
+		"1h2m3s": 1*time.Hour + 2*time.Minute + 3*time.Second,
+		"0":      time.Duration(0),
+		"60":     60 * time.Second,
+		"120":    2 * time.Minute,
+		"3600":   time.Hour,
+		"-0":     time.Duration(0),
+		"-1":     time.Duration(math.MaxInt64),
+		"-1m":    time.Duration(math.MaxInt64),
+		// invalid values
+		" ":   5 * time.Minute,
+		"???": 5 * time.Minute,
+		"1d":  5 * time.Minute,
+		"1y":  5 * time.Minute,
+		"1w":  5 * time.Minute,
+	}
+
+	for tt, expect := range cases {
+		t.Run(tt, func(t *testing.T) {
+			t.Setenv("OLLAMA_KEEP_ALIVE", tt)
+			if actual := KeepAlive(); actual != expect {
+				t.Errorf("%s: expected %s, got %s", tt, expect, actual)
+			}
+		})
+	}
+}
+
+func TestVar(t *testing.T) {
+	cases := map[string]string{
+		"value":       "value",
+		" value ":     "value",
+		" 'value' ":   "value",
+		` "value" `:   "value",
+		" ' value ' ": " value ",
+		` " value " `: " value ",
+	}
+
+	for k, v := range cases {
+		t.Run(k, func(t *testing.T) {
+			t.Setenv("OLLAMA_VAR", k)
+			if s := Var("OLLAMA_VAR"); s != v {
+				t.Errorf("%s: expected %q, got %q", k, v, s)
+			}
+		})
+	}
+}

ollama/examples/.gitignore

+node_modules
+bun.lockb
+.vscode
+# OSX
+.DS_STORE
+
+
+# Models
+models/
+
+# Local Chroma db
+.chroma/
+db/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

ollama/examples/README.md

+# Examples
+
+This directory contains different examples of using Ollama.

ollama/examples/flyio/.gitignore

+fly.toml

ollama/examples/flyio/README.md

+# Deploy Ollama to Fly.io
+
+> Note: this example exposes a public endpoint and does not configure authentication. Use with care.
+
+## Prerequisites
+
+- Ollama: https://ollama.com/download
+- Fly.io account. Sign up for a free account: https://fly.io/app/sign-up
+
+## Steps
+
+1. Login to Fly.io
+
+    ```bash
+    fly auth login
+    ```
+
+1. Create a new Fly app
+
+    ```bash
+    fly launch --name <name> --image ollama/ollama --internal-port 11434 --vm-size shared-cpu-8x --now
+    ```
+
+1. Pull and run `orca-mini:3b`
+
+    ```bash
+    OLLAMA_HOST=https://<name>.fly.dev ollama run orca-mini:3b
+    ```
+
+`shared-cpu-8x` is a free-tier eligible machine type. For better performance, switch to a `performance` or `dedicated` machine type or attach a GPU for hardware acceleration (see below).
+
+## (Optional) Persistent Volume
+
+By default Fly Machines use ephemeral storage which is problematic if you want to use the same model across restarts without pulling it again. Create and attach a persistent volume to store the downloaded models:
+
+1. Create the Fly Volume
+
+    ```bash
+    fly volume create ollama
+    ```
+
+1. Update `fly.toml` and add `[mounts]`
+
+    ```toml
+    [mounts]
+      source = "ollama"
+      destination = "/mnt/ollama/models"
+    ```
+
+1. Update `fly.toml` and add `[env]`
+
+    ```toml
+    [env]
+      OLLAMA_MODELS = "/mnt/ollama/models"
+    ```
+
+1. Deploy your app
+
+    ```bash
+    fly deploy
+    ```
+
+## (Optional) Hardware Acceleration
+
+Fly.io GPU is currently in waitlist. Sign up for the waitlist: https://fly.io/gpu
+
+Once you've been accepted, create the app with the additional flags `--vm-gpu-kind a100-pcie-40gb` or `--vm-gpu-kind a100-pcie-80gb`.

ollama/examples/go-chat/main.go

+package main
+
+import (
+	"context"
+	"fmt"
+	"log"
+
+	"github.com/ollama/ollama/api"
+)
+
+func main() {
+	client, err := api.ClientFromEnvironment()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	messages := []api.Message{
+		api.Message{
+			Role:    "system",
+			Content: "Provide very brief, concise responses",
+		},
+		api.Message{
+			Role:    "user",
+			Content: "Name some unusual animals",
+		},
+		api.Message{
+			Role:    "assistant",
+			Content: "Monotreme, platypus, echidna",
+		},
+		api.Message{
+			Role:    "user",
+			Content: "which of these is the most dangerous?",
+		},
+	}
+
+	ctx := context.Background()
+	req := &api.ChatRequest{
+		Model:    "llama3.1",
+		Messages: messages,
+	}
+
+	respFunc := func(resp api.ChatResponse) error {
+		fmt.Print(resp.Message.Content)
+		return nil
+	}
+
+	err = client.Chat(ctx, req, respFunc)
+	if err != nil {
+		log.Fatal(err)
+	}
+}

ollama/examples/go-generate-streaming/main.go

+package main
+
+import (
+	"context"
+	"fmt"
+	"log"
+
+	"github.com/ollama/ollama/api"
+)
+
+func main() {
+	client, err := api.ClientFromEnvironment()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	// By default, GenerateRequest is streaming.
+	req := &api.GenerateRequest{
+		Model:  "gemma2",
+		Prompt: "how many planets are there?",
+	}
+
+	ctx := context.Background()
+	respFunc := func(resp api.GenerateResponse) error {
+		// Only print the response here; GenerateResponse has a number of other
+		// interesting fields you want to examine.
+
+		// In streaming mode, responses are partial so we call fmt.Print (and not
+		// Println) in order to avoid spurious newlines being introduced. The
+		// model will insert its own newlines if it wants.
+		fmt.Print(resp.Response)
+		return nil
+	}
+
+	err = client.Generate(ctx, req, respFunc)
+	if err != nil {
+		log.Fatal(err)
+	}
+	fmt.Println()
+}

ollama/examples/go-generate/main.go

+package main
+
+import (
+	"context"
+	"fmt"
+	"log"
+
+	"github.com/ollama/ollama/api"
+)
+
+func main() {
+	client, err := api.ClientFromEnvironment()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	req := &api.GenerateRequest{
+		Model:  "gemma2",
+		Prompt: "how many planets are there?",
+
+		// set streaming to false
+		Stream: new(bool),
+	}
+
+	ctx := context.Background()
+	respFunc := func(resp api.GenerateResponse) error {
+		// Only print the response here; GenerateResponse has a number of other
+		// interesting fields you want to examine.
+		fmt.Println(resp.Response)
+		return nil
+	}
+
+	err = client.Generate(ctx, req, respFunc)
+	if err != nil {
+		log.Fatal(err)
+	}
+}

ollama/examples/go-http-generate/main.go

+package main
+
+import (
+	"bytes"
+	"fmt"
+	"io"
+	"log"
+	"net/http"
+	"os"
+)
+
+func main() {
+	body := []byte(`{"model":"mistral"}`)
+	resp, err := http.Post("http://localhost:11434/api/generate", "application/json", bytes.NewBuffer(body))
+
+	if err != nil {
+		fmt.Print(err.Error())
+		os.Exit(1)
+	}
+
+	defer resp.Body.Close()
+
+	responseData, err := io.ReadAll(resp.Body)
+	if err != nil {
+		log.Fatal(err)
+	}
+	fmt.Println(string(responseData))
+
+}

ollama/examples/go-multimodal/main.go

+package main
+
+import (
+	"context"
+	"fmt"
+	"log"
+	"os"
+
+	"github.com/ollama/ollama/api"
+)
+
+func main() {
+	if len(os.Args) <= 1 {
+		log.Fatal("usage: <image name>")
+	}
+
+	imgData, err := os.ReadFile(os.Args[1])
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	client, err := api.ClientFromEnvironment()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	req := &api.GenerateRequest{
+		Model:  "llava",
+		Prompt: "describe this image",
+		Images: []api.ImageData{imgData},
+	}
+
+	ctx := context.Background()
+	respFunc := func(resp api.GenerateResponse) error {
+		// In streaming mode, responses are partial so we call fmt.Print (and not
+		// Println) in order to avoid spurious newlines being introduced. The
+		// model will insert its own newlines if it wants.
+		fmt.Print(resp.Response)
+		return nil
+	}
+
+	err = client.Generate(ctx, req, respFunc)
+	if err != nil {
+		log.Fatal(err)
+	}
+	fmt.Println()
+}

ollama/examples/go-pull-progress/main.go

+package main
+
+import (
+	"context"
+	"fmt"
+	"log"
+
+	"github.com/ollama/ollama/api"
+)
+
+func main() {
+	client, err := api.ClientFromEnvironment()
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	ctx := context.Background()
+
+	req := &api.PullRequest{
+		Model: "mistral",
+	}
+	progressFunc := func(resp api.ProgressResponse) error {
+		fmt.Printf("Progress: status=%v, total=%v, completed=%v\n", resp.Status, resp.Total, resp.Completed)
+		return nil
+	}
+
+	err = client.Pull(ctx, req, progressFunc)
+	if err != nil {
+		log.Fatal(err)
+	}
+}

ollama/examples/jupyter-notebook/README.md

+# Ollama Jupyter Notebook
+
+This example downloads and installs Ollama in a Jupyter instance such as Google Colab. It will start the Ollama service and expose an endpoint using `ngrok` which can be used to communicate with the Ollama instance remotely.
+
+For best results, use an instance with GPU accelerator.

ollama/examples/jupyter-notebook/ollama.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "93f59dcb-c588-41b8-a792-55d88ade739c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Download and run the Ollama Linux install script\n",
+    "!curl -fsSL https://ollama.com/install.sh | sh\n",
+    "!command -v systemctl >/dev/null && sudo systemctl stop ollama"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "658c147e-c7f8-490e-910e-62b80f577dda",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install aiohttp pyngrok\n",
+    "\n",
+    "import os\n",
+    "import asyncio\n",
+    "from aiohttp import ClientSession\n",
+    "\n",
+    "# Set LD_LIBRARY_PATH so the system NVIDIA library becomes preferred\n",
+    "# over the built-in library. This is particularly important for \n",
+    "# Google Colab which installs older drivers\n",
+    "os.environ.update({'LD_LIBRARY_PATH': '/usr/lib64-nvidia'})\n",
+    "\n",
+    "async def run(cmd):\n",
+    "  '''\n",
+    "  run is a helper function to run subcommands asynchronously.\n",
+    "  '''\n",
+    "  print('>>> starting', *cmd)\n",
+    "  p = await asyncio.subprocess.create_subprocess_exec(\n",
+    "      *cmd,\n",
+    "      stdout=asyncio.subprocess.PIPE,\n",
+    "      stderr=asyncio.subprocess.PIPE,\n",
+    "  )\n",
+    "\n",
+    "  async def pipe(lines):\n",
+    "    async for line in lines:\n",
+    "      print(line.strip().decode('utf-8'))\n",
+    "\n",
+    "  await asyncio.gather(\n",
+    "      pipe(p.stdout),\n",
+    "      pipe(p.stderr),\n",
+    "  )\n",
+    "\n",
+    "\n",
+    "await asyncio.gather(\n",
+    "    run(['ollama', 'serve']),\n",
+    "    run(['ngrok', 'http', '--log', 'stderr', '11434']),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e7735a55-9aad-4caf-8683-52e2163ba53b",
+   "metadata": {},
+   "source": [
+    "The previous cell starts two processes, `ollama` and `ngrok`. The log output will show a line like the following which describes the external address.\n",
+    "\n",
+    "```\n",
+    "t=2023-11-12T22:55:56+0000 lvl=info msg=\"started tunnel\" obj=tunnels name=command_line addr=http://localhost:11434 url=https://8249-34-125-179-11.ngrok.io\n",
+    "```\n",
+    "\n",
+    "The external address in this case is `https://8249-34-125-179-11.ngrok.io` which can be passed into `OLLAMA_HOST` to access this instance.\n",
+    "\n",
+    "```bash\n",
+    "export OLLAMA_HOST=https://8249-34-125-179-11.ngrok.io\n",
+    "ollama list\n",
+    "ollama run mistral\n",
+    "```"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

ollama/examples/kubernetes/README.md

+# Deploy Ollama to Kubernetes
+
+## Prerequisites
+
+- Ollama: https://ollama.com/download
+- Kubernetes cluster. This example will use Google Kubernetes Engine.
+
+## Steps
+
+1. Create the Ollama namespace, deployment, and service
+
+   ```bash
+   kubectl apply -f cpu.yaml
+   ```
+
+## (Optional) Hardware Acceleration
+
+Hardware acceleration in Kubernetes requires NVIDIA's [`k8s-device-plugin`](https://github.com/NVIDIA/k8s-device-plugin) which is deployed in Kubernetes in form of daemonset. Follow the link for more details.
+
+Once configured, create a GPU enabled Ollama deployment.
+
+```bash
+kubectl apply -f gpu.yaml
+```
+
+## Test
+
+1. Port forward the Ollama service to connect and use it locally
+
+   ```bash
+   kubectl -n ollama port-forward service/ollama 11434:80
+   ```
+
+1. Pull and run a model, for example `orca-mini:3b`
+
+   ```bash
+   ollama run orca-mini:3b
+   ```
\ No newline at end of file

ollama/examples/kubernetes/cpu.yaml

+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: ollama
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: ollama
+  namespace: ollama
+spec:
+  selector:
+    matchLabels:
+      name: ollama
+  template:
+    metadata:
+      labels:
+        name: ollama
+    spec:
+      containers:
+      - name: ollama
+        image: ollama/ollama:latest
+        ports:
+        - name: http
+          containerPort: 11434
+          protocol: TCP
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: ollama
+  namespace: ollama
+spec:
+  type: ClusterIP
+  selector:
+    name: ollama
+  ports:
+  - port: 80
+    name: http
+    targetPort: http
+    protocol: TCP