feat: Draft ollama test

.github/workflows/test_gemini.yml

@@ -0,0 +1,33 @@
+name: test | gemini
+
+on:
+  workflow_dispatch:
+  pull_request:
+    types: [labeled, synchronize]
+
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  run_simple_example_test:
+      uses: ./.github/workflows/reusable_python_example.yml
+      with:
+        example-location: ./examples/python/simple_example.py
+      secrets:
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        GRAPHISTRY_USERNAME: ${{ secrets.GRAPHISTRY_USERNAME }}
+        GRAPHISTRY_PASSWORD: ${{ secrets.GRAPHISTRY_PASSWORD }}
+        EMBEDDING_PROVIDER: "gemini"
+        EMBEDDING_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+        EMBEDDING_MODEL: "gemini/text-embedding-004"
+        EMBEDDING_ENDPOINT: "https://generativelanguage.googleapis.com/v1beta/models/text-embedding-004"
+        EMBEDDING_API_VERSION: "v1beta"
+        EMBEDDING_DIMENSIONS: 768
+        EMBEDDING_MAX_TOKENS: 8076
+        LLM_PROVIDER: "gemini"
+        LLM_API_KEY: ${{ secrets.GEMINI_API_KEY }}
+        LLM_MODEL: "gemini/gemini-1.5-flash"
+        LLM_ENDPOINT: "https://generativelanguage.googleapis.com/"
+        LLM_API_VERSION: "v1beta"

.github/workflows/test_ollama.yml

@@ -0,0 +1,84 @@
+name: test | ollama
+
+on:
+  workflow_dispatch:
+  pull_request:
+    types: [ labeled, synchronize ]
+
+jobs:
+
+  run_simple_example_test:
+
+    runs-on: ubuntu-latest
+    services:
+      ollama:
+        image: ollama/ollama
+        ports:
+          - 11434:11434
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12.x'
+
+      - name: Install Poetry
+        uses: snok/[email protected]
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+          installer-parallel: true
+
+      - name: Install dependencies
+        run: |
+          poetry install --no-interaction --all-extras
+
+      - name: Install ollama
+        run: curl -fsSL https://ollama.com/install.sh | sh
+      - name: Run ollama
+        run: |
+          ollama serve &
+          ollama pull llama3.2 &
+          ollama pull avr/sfr-embedding-mistral:latest
+      - name: Call ollama API
+        run: |
+          curl -d '{"model": "llama3.2", "stream": false, "prompt":"Whatever I say, asnwer with Yes"}' http://localhost:11434/api/generate
+
+      - name: Wait for Ollama to be ready
+        run: |
+          for i in {1..30}; do
+            if curl -s http://localhost:11434/api/tags > /dev/null; then
+              echo "Ollama is ready"
+              exit 0
+            fi
+            echo "Waiting for Ollama... attempt $i"
+            sleep 2
+          done
+          echo "Ollama failed to start"
+          exit 1
+
+      - name: Dump Docker logs
+        run: |
+          docker ps
+          docker logs $(docker ps --filter "ancestor=ollama/ollama" --format "{{.ID}}")
+
+
+      - name: Run example test
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          GRAPHISTRY_USERNAME: ${{ secrets.GRAPHISTRY_USERNAME }}
+          GRAPHISTRY_PASSWORD: ${{ secrets.GRAPHISTRY_PASSWORD }}
+          PYTHONFAULTHANDLER: 1
+          LLM_API_KEY: "ollama"
+          LLM_PROVIDER: "ollama"
+          LLM_ENDPOINT: "http://127.0.0.1:11434/api/generate"
+          LLM_MODEL: "ollama/llama3.2"
+          EMBEDDING_PROVIDER: "ollama"
+          EMBEDDING_MODEL: "avr/sfr-embedding-mistral:latest"
+          EMBEDDING_ENDPOINT: "http://127.0.0.1:11434/api/embeddings"
+          EMBEDDING_DIMENSIONS: "4096"
+          HUGGINGFACE_TOKENIZER: "Salesforce/SFR-Embedding-Mistral"
+        run: poetry run python ./examples/python/simple_example.py

.github/workflows/upgrade_deps.yml

@@ -2,8 +2,29 @@ name: Update Poetry Dependencies
 
 on:
   schedule:
-    - cron: '0 3 * * 0'
+    - cron: '0 3 * * 0'  # Runs at 3 AM every Sunday
+  push:
+    paths:
+      - 'poetry.lock'
+      - 'pyproject.toml'
+    branches:
+      - main
+      - dev
+  pull_request:
+    paths:
+      - 'poetry.lock'
+      - 'pyproject.toml'
+    types: [opened, synchronize, reopened]
+    branches:
+      - main
+      - dev
   workflow_dispatch:
+    inputs:
+      debug_enabled:
+        type: boolean
+        description: 'Run the update with debug logging'
+        required: false
+        default: false
 
 jobs:
   update-dependencies:

cognee/infrastructure/llm/ollama/adapter.py

@@ -1,20 +1,28 @@
+from sys import api_version
 from typing import Type
 from pydantic import BaseModel
 import instructor
 from cognee.infrastructure.llm.llm_interface import LLMInterface
 from cognee.infrastructure.llm.config import get_llm_config
 from openai import OpenAI
-
+import base64
+from pathlib import Path
+import os
 
 class OllamaAPIAdapter(LLMInterface):
-    """Adapter for a Generic API LLM provider using instructor with an OpenAI backend."""
+    """Adapter for a Ollama API LLM provider using instructor with an OpenAI backend."""
+
+    api_version: str
+
+    MAX_RETRIES = 5
 
-    def __init__(self, endpoint: str, api_key: str, model: str, name: str, max_tokens: int):
+    def __init__(self, endpoint: str, api_key: str, model: str, name: str, max_tokens: int, api_version: str = None) -> None:
         self.name = name
         self.model = model
         self.api_key = api_key
         self.endpoint = endpoint
         self.max_tokens = max_tokens
+        self.api_version= api_version
 
         self.aclient = instructor.from_openai(
             OpenAI(base_url=self.endpoint, api_key=self.api_key), mode=instructor.Mode.JSON
@@ -42,3 +50,54 @@ async def acreate_structured_output(
         )
 
         return response
+
+
+    def create_transcript(self, input):
+        """Generate a audio transcript from a user query."""
+
+        if not os.path.isfile(input):
+            raise FileNotFoundError(f"The file {input} does not exist.")
+
+        # with open(input, 'rb') as audio_file:
+        #     audio_data = audio_file.read()
+
+        transcription = self.aclient.transcription(
+            model=self.transcription_model,
+            file=Path(input),
+            api_key=self.api_key,
+            api_base=self.endpoint,
+            api_version=self.api_version,
+            max_retries=self.MAX_RETRIES,
+        )
+
+        return transcription
+
+    def transcribe_image(self, input) -> BaseModel:
+        with open(input, "rb") as image_file:
+            encoded_image = base64.b64encode(image_file.read()).decode("utf-8")
+
+        return self.aclient.completion(
+            model=self.model,
+            messages=[
+                {
+                    "role": "user",
+                    "content": [
+                        {
+                            "type": "text",
+                            "text": "What’s in this image?",
+                        },
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": f"data:image/jpeg;base64,{encoded_image}",
+                            },
+                        },
+                    ],
+                }
+            ],
+            api_key=self.api_key,
+            api_base=self.endpoint,
+            api_version=self.api_version,
+            max_tokens=300,
+            max_retries=self.MAX_RETRIES,
+        )