Bump version: 1.4.0 → 1.5.0

From experience elsewhere, there seem to be some providers that default
to streaming.

Also update dependencies in pyproject.toml to match requirements.txt.

.github/workflows/publish.yml

@@ -8,17 +8,19 @@ on:
     paths:
       - "pyproject.toml"
 
+permissions:
+  issues: write
+
 jobs:
   publish-node:
     name: Publish Custom Node to registry
     runs-on: ubuntu-latest
-    # if this is a forked repository. Skipping the workflow.
-    if: github.event.repository.fork == false 
+    if: ${{ github.repository_owner == 'asaddi' }}
     steps:
       - name: Check out code
         uses: actions/checkout@v4
       - name: Publish Custom Node
-        uses: Comfy-Org/publish-node-action@main
+        uses: Comfy-Org/publish-node-action@v1
         with:
           ## Add your own personal access token to your Github Repository secrets and reference it here.
           personal_access_token: ${{ secrets.REGISTRY_ACCESS_TOKEN }}

README.md

@@ -1,3 +1,5 @@
+
+
 # Yet Another LLM Node (for ComfyUI)
 
 Yet another set of LLM nodes for [ComfyUI](https://github.com/comfyanonymous/ComfyUI). This one only supports OpenAI-like APIs, but of course can be used with local LLM providers such as [llama.cpp](https://github.com/ggerganov/llama.cpp) (and ollama, LM Studio, among many others).
@@ -69,6 +71,10 @@ The input is optional, meaning you can mute the node leading into it or even dis
 
 The node will output whatever is currently being displayed in the textbox. The node text will also be saved in exported workflows and generated images.
 
+## "Prepend/Append" Node
+
+A simple utility node that takes a text input and optionally adds a prefix and/or suffix to it. This is useful for dynamically injecting instructions or context into prompts without altering the source text, as demonstrated in the `prompt-optimizer` example workflow.
+
 ## My Related Projects
 
 * https://github.com/asaddi/YALLM-LlamaVision Basic ComfyUI node for Llama 3.2 Vision. Sampler/model nodes are cross-compatible with this project.

models.yaml.example

@@ -6,6 +6,16 @@ models:
     api_key: none
     model: whatever
 
+  - name: "[LOCAL] LM Studio"
+    base_url: http://localhost:1234/v1
+    api_key: none
+    model: changeme
+
+  - name: "[LOCAL] Ollama"
+    base_url: http://localhost:11434/v1
+    api_key: none
+    model: changeme
+
 # Example of using a remote endpoint
 # If prefixed with "os.environ/" (similar to LiteLLM), base_url and/or api_key
 # will take their value from the named environment variable.

nodes.py

@@ -6,9 +6,9 @@ from typing import Any, Optional
 
 from aiohttp import web
 from aiohttp.web_request import Request
-import openai
 from PIL.Image import Image
 from pydantic import BaseModel
+import requests
 import torchvision.transforms.functional as F
 import yaml
 
@@ -347,20 +347,19 @@ SamplerSetting = tuple[str, Any]
 
 class LLMModel:
     def __init__(self, prov_def: ProviderDefinition, model: str | None = None):
-        self._llm = openai.OpenAI(
-            base_url=prov_def.resolve_base_url(),
-            api_key=(
-                prov_def.resolve_api_key() or "none"
-            ),  # openai package requires something for API key
-        )
+        self._base_url = prov_def.resolve_base_url()
+        self._headers = {}
+        if (api_key := prov_def.resolve_api_key()) and api_key != "none":
+            self._headers["authorization"] = f"Bearer {api_key}"
         if model is None:
             self._model = getattr(prov_def, "model", None)
         else:
             self._model = model
 
     def get_models(self):
-        models = list(self._llm.models.list())
-        return [m.id for m in models]
+        with requests.get(self._base_url + "/models", headers=self._headers) as r:
+            models_json = r.json()
+        return [m["id"] for m in models_json["data"]]
 
     def chat_completion(
         self,
@@ -404,34 +403,35 @@ class LLMModel:
 
         sampler_order = []
         extra_args = {}
-        extra_body = {}
         for k, v in samplers:
             sampler_order.append(k)
-            if k in (
-                "temperature",
-                "top_p",
-            ):  # The only ones supported directly by openai package
-                extra_args[k] = v
-            else:
-                # The rest have to go into "extra_body"
-                extra_body[k] = v
-        extra_body["samplers"] = (
+            extra_args[k] = v
+        extra_args["samplers"] = (
             sampler_order  # Hopefully won't cause an issue for non-llama.cpp endpoints
         )
 
         if seed is not None:
             extra_args["seed"] = seed
 
-        # print(f'extra_args = {repr(extra_args)}')
-        # print(f'extra_body = {repr(extra_body)}')
+        # print(f"extra_args = {repr(extra_args)}")
 
-        output = self._llm.chat.completions.create(
-            messages=messages, model=self._model, extra_body=extra_body, **extra_args
-        )
+        req_json = {
+            "model": self._model,
+            "messages": messages,
+            "stream": False,
+        }
+        req_json.update(extra_args)
 
-        # TODO Since we're not streaming, we'll need some sort of timeout. How to specify that?
+        # TODO Since we're not streaming, we'll need some sort of timeout. TODO specify that
+        with requests.post(
+            self._base_url + "/chat/completions", json=req_json, headers=self._headers
+        ) as r:
+            output = r.json()
 
-        return output.choices[0].message.content
+        if choices := output.get("choices", []):
+            return choices[0]["message"]["content"]
+        else:
+            return ""
 
 
 class LLMProvider:

providers.yaml.example

@@ -5,6 +5,14 @@ providers:
     base_url: http://localhost:8080/v1
     api_key: none
 
+  - name: "[LOCAL] LM Studio"
+    base_url: http://localhost:1234/v1
+    api_key: none
+
+  - name: "[LOCAL] Ollama"
+    base_url: http://localhost:11434/v1
+    api_key: none
+
 # Example of using a remote endpoint
 # If prefixed with "os.environ/" (similar to LiteLLM), base_url and/or api_key
 # will take their value from the named environment variable.

pyproject.toml

@@ -1,12 +1,14 @@
 [project]
 name = "comfyui-yallm-node"
 description = "Yet another set of LLM nodes for ComfyUI (for local/remote OpenAI-like APIs, multi-modal models supported)"
-version = "1.4.0"
+version = "1.5.0"
 license = {file = "LICENSE.txt"}
 dependencies = [
-    "openai",
+    "pillow",
     "pydantic",
-    "pyyaml"
+    "pyyaml",
+    "requests",
+    "torchvision"
 ]
 
 [project.urls]
@@ -19,7 +21,7 @@ DisplayName = "ComfyUI-YALLM-node"
 Icon = ""
 
 [tool.bumpversion]
-current_version = "1.4.0"
+current_version = "1.5.0"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)"
 serialize = ["{major}.{minor}.{patch}"]
 search = "{current_version}"

requirements.txt

@@ -1,7 +1,6 @@
-openai
-pydantic
-
 # These should already be installed by ComfyUI
 pillow
+pydantic
 pyyaml
+requests
 torchvision

utils.py

@@ -1,3 +1,4 @@
+# Copyright (c) 2024 Allan Saddi <allan@saddi.com>
 class PromptUtils:
     def __init__(self, prompt):
         self.prompt = prompt
@@ -68,7 +69,7 @@ class WorkflowUtils:
             and (workflow := self.extra_pnginfo.get("workflow")) is not None
             and (nodes := workflow.get("nodes")) is not None
         ):
-            node_id = int(node_id)
+            node_id = str(node_id)
             # TODO For the time being, we aren't caching anything.
             # Concievably, if there are a large number of nodes, a lot of time
             # could be wasted searching.
@@ -87,3 +88,18 @@ class WorkflowUtils:
             # TODO When would there be a mismatch?
             if slot < len(values):
                 values[slot] = value
+
+
+class AnyType(str):
+    def __ne__(self, other):
+        if self == "*":
+            # If we're the wildcard, match anything
+            return False
+        return super().__ne__(other)
+
+
+class ComboType(str):
+    def __ne__(self, other):
+        if self == "*" and isinstance(other, list):
+            return False
+        return True