matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-11 08:17:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update readmes, requirements, packagejsons, etc for all examples (#1452)

Browse Source 
Most of the examples needed updates of Readmes to show how to run them. Some of the requirements.txt files had extra content that wasn't needed, or missing altogether. Apparently some folks like to run npm start
to run typescript, so a script was added to all typescript examples which
hadn't been done before.

Basically just a lot of cleanup.

Signed-off-by: Matt Williams <m@technovangelist.com>
This commit is contained in:
Matt Williams
2023-12-22 09:10:41 -08:00
committed by GitHub
parent 291700c92d
commit 5a85070c22
26 changed files with 346 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
examples/typescript-simplechat/package.json
View File

@@ -1 +1,12 @@
{ "dependencies": { "@types/node": "^20.10.4", "prompt-sync": "^4.2.0", "readline": "^1.3.0" } }
{
"scripts": {
"start": "tsx client.ts"
},
"dependencies": {
"@types/node": "^20.10.4",
"prompt-sync": "^4.2.0",
"readline": "^1.3.0",
"tsx": "^4.6.2",
"typescript": "^5.3.3"
}
}

10
examples/typescript-simplechat/readme.md
View File

@@ -1,14 +1,10 @@
# Simple Chat Example
The **chat** endpoint is one of two ways to generate text from an LLM with Ollama. At a high level you provide the endpoint an array of message objects with a role and content specified. Then with each output and prompt, you add more messages, which builds up the history.
The **chat** endpoint, available as of v0.1.14, is one of two ways to generate text from an LLM with Ollama. At a high level, you provide the endpoint an array of message objects with a role and content specified. Then with each output and prompt, you add more messages, which builds up the history.
## Run the Example
There are a few ways to run this, just like any Typescript code:
1. Compile with `tsc` and then run it with `node client.js`.
2. Install `tsx` and run it with `tsx client.ts`.
3. Install `bun` and run it with `bun client.ts`.
`npm start`
## Review the Code
@@ -30,7 +26,7 @@ With the **generate** endpoint, you need to provide a `prompt`. But with **chat*
The final JSON object doesn't provide the full content, so you will need to build the content yourself. In this example, **chat** takes the full array of messages and outputs the resulting message from this call of the chat endpoint.
In the **askQuestion** function, we collect `user_input` and add it as a message to our messages and that is passed to the chat function. When the LLM is done responding the output is added as another message to the messages array.
In the **askQuestion** function, we collect `user_input` and add it as a message to our messages, and that is passed to the chat function. When the LLM is done responding, the output is added as another message to the messages array.
At the end, you will see a printout of all the messages.