Combined Cloud Managed Services

User Tools

Site Tools

wiki:ai:cli-workspace-deployment-upload

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
wiki:ai:cli-workspace-deployment-upload [2025/06/03 21:19] – ddehamerwiki:ai:cli-workspace-deployment-upload [2025/06/04 15:51] (current) – ddehamer
Line 1: Line 1:
 ====== CLI ML Workspace Transcript ====== ====== CLI ML Workspace Transcript ======
 +
 +This turned out to take way longer than expected due to ChatGPT getting into a loop and breaking one thing to fix another and then not keeping track of it's own changes.  To finally fix this I had to point out a flaw in it's process so it gave me the right script and then it finally worked as shown below.  Beneath the scripts is the transcript of the conversations to get me to the working end product.
 +
 +===== Working Scripts =====
 +
 +train.py
 +<code>
 +#!/Users/don.dehamer/.local/pipx/venvs/requests/bin/python3.9
 +
 +import pandas as pd
 +import numpy as np
 +from sklearn.model_selection import train_test_split
 +from sklearn.preprocessing import OneHotEncoder
 +from sklearn.linear_model import Ridge
 +from sklearn.metrics import mean_squared_error
 +from sklearn.compose import ColumnTransformer
 +from sklearn.pipeline import Pipeline
 +import joblib
 +
 +# Load data
 +df = pd.read_csv("collectibles.csv")
 +
 +# Features and target
 +features = ["character", "figure_name", "property", "type", "manufacturer", "list_price"]
 +target = "approximate_value"
 +
 +X = df[features]
 +y = df[target]
 +
 +# Train/test split
 +X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 +
 +# Preprocessing
 +categorical_features = ["character", "figure_name", "property", "type", "manufacturer"]
 +numeric_features = ["list_price"]
 +
 +preprocessor = ColumnTransformer(
 +    transformers=[
 +        ("cat", OneHotEncoder(handle_unknown="ignore"), categorical_features),
 +        ("num", "passthrough", numeric_features)
 +    ]
 +)
 +
 +# Build pipeline
 +model = Pipeline(steps=[
 +    ("preprocessor", preprocessor),
 +    ("regressor", Ridge(alpha=1.0))
 +])
 +
 +# Train
 +model.fit(X_train, y_train)
 +
 +# Evaluate
 +y_pred = model.predict(X_test)
 +rmse = np.sqrt(mean_squared_error(y_test, y_pred))
 +print(f"RMSE: {rmse:.2f}")
 +
 +# Save model
 +joblib.dump(model, "collectibles_model.joblib")
 +</code>
 +
 +env.yml
 +<code>
 +name: collectibles-env
 +channels:
 +  - conda-forge
 +  - defaults
 +dependencies:
 +  - python=3.9
 +  - pip
 +  - pip:
 +      - numpy==1.26.4
 +      - pandas==2.2.2
 +      - scikit-learn==1.6.1
 +      - joblib
 +      - azureml-inference-server-http
 +</code>
 +
 +score.py
 +<code>
 +#!/Users/don.dehamer/.local/pipx/venvs/requests/bin/python3.9
 +import json
 +import os
 +import joblib
 +import pandas as pd
 +
 +model = None
 +
 +def init():
 +    global model
 +    model_path = os.path.join(os.getenv("AZUREML_MODEL_DIR"), "collectibles_model.joblib")
 +    model = joblib.load(model_path)
 +
 +def run(request):
 +    try:
 +        # Azure ML sends the request body as a string; parse it
 +        data = json.loads(request)
 +
 +        # Ensure we're dealing with a list of records
 +        if isinstance(data, list):
 +            df = pd.DataFrame(data)
 +        elif isinstance(data, dict) and "input_data" in data:
 +            df = pd.DataFrame(data["input_data"])
 +        else:
 +            return json.dumps({"error": "Invalid input format. Must be list or dict with 'input_data'."})
 +
 +        predictions = model.predict(df)
 +        return json.dumps(predictions.tolist())
 +    except Exception as e:
 +        return json.dumps({"error": str(e)})
 +</code>
 +
 +deploy_to_azure_clean.py
 +<code>
 +#!/Users/don.dehamer/.local/pipx/venvs/requests/bin/python3.9
 +
 +from azure.identity import DefaultAzureCredential
 +from azure.ai.ml import MLClient
 +from azure.ai.ml.entities import (
 +    ManagedOnlineEndpoint,
 +    ManagedOnlineDeployment,
 +    Model,
 +    Environment,
 +    CodeConfiguration
 +)
 +import uuid
 +
 +# Set your Azure environment details
 +subscription_id = "baa29726-b3e6-4910-bb9b-b585c655322c"
 +resource_group = "don-test-rg-SCUS"
 +workspace_name = "don-ml-workspace-fixed"
 +
 +# Connect to Azure ML workspace
 +ml_client = MLClient(
 +    DefaultAzureCredential(),
 +    subscription_id,
 +    resource_group,
 +    workspace_name
 +)
 +
 +# Register the model
 +model = Model(
 +    path="collectibles_model.joblib",
 +    name="collectibles-model",
 +    description="Predicts collectible value",
 +    type="custom_model"
 +)
 +registered_model = ml_client.models.create_or_update(model)
 +
 +# Create the environment
 +env = Environment(
 +    name="collectibles-env",
 +    description="Environment for collectibles model with inference server",
 +    image="mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04",
 +    conda_file="env.yml"
 +)
 +ml_client.environments.create_or_update(env)
 +
 +# Generate a unique endpoint name
 +endpoint_name = f"collectibles-endpoint-{str(uuid.uuid4())[:8]}"
 +
 +# Create the endpoint
 +endpoint = ManagedOnlineEndpoint(
 +    name=endpoint_name,
 +    description="Collectibles value predictor",
 +    auth_mode="key"
 +)
 +ml_client.begin_create_or_update(endpoint).result()
 +
 +# Deploy the model
 +deployment = ManagedOnlineDeployment(
 +    name="blue",
 +    endpoint_name=endpoint_name,
 +    model=registered_model,
 +    environment=env,
 +    code_configuration=CodeConfiguration(
 +        code="./",
 +        scoring_script="score.py"
 +    ),
 +    instance_type="Standard_DS3_v2",
 +    instance_count=1
 +)
 +ml_client.begin_create_or_update(deployment).result()
 +
 +# Set default deployment
 +existing_endpoint = ml_client.online_endpoints.get(name=endpoint_name)
 +existing_endpoint.defaults = {"deployment_name": "blue"}
 +ml_client.begin_create_or_update(existing_endpoint).result()
 +
 +print(f"✅ Deployment complete! Endpoint name: {endpoint_name}")
 +</code>
 +
 +test_endpoint.py
 +<code>
 +#!/Users/don.dehamer/.local/pipx/venvs/requests/bin/python3.9
 +
 +import requests
 +import json
 +
 +# Replace this with your actual endpoint URL
 +endpoint = "https://<ENDPOINT>.southcentralus.inference.ml.azure.com/score"
 +api_key = "<API KEY>"
 +
 +headers = {
 +    "Content-Type": "application/json",
 +    "Authorization": f"Bearer {api_key}"  # If you're using key auth and not AAD, use: "Bearer {api-key}"
 +}
 +
 +data = [
 +    {
 +        "character": "Mario",
 +        "figure_name": "Fire Mario",
 +        "property": "Nintendo",
 +        "type": "Figure",
 +        "quantity": 1,
 +        "manufacturer": "Jakks Pacific",
 +        "list_price": 9.99,
 +        "total_cost": 6.99,
 +        "approximate_value": 15.00,
 +        "location": "Shelf A"
 +    }
 +]
 +
 +response = requests.post(endpoint, json=data, headers=headers)
 +
 +print("✅ Response from endpoint:")
 +print(response.text)
 +</code>
 +
 +===== Important Observations and Commands =====
 +
 +  - After successful deployment you have to gather 3 pieces of information.
 +    - The endpoint name.  This will be shown during deployment but will also be listed in endpoints under ML.
 +    - The endpoint URL.  This will be shown under the endpoint in the portal.
 +    - The access key.  Gotten by running a az cli command while logged in within a terminal.
 +      - i.e. az ml online-endpoint get-credentials --name collectibles-endpoint-11ee416b --resource-group don-test-rg-SCUS --workspace-name don-ml-workspace-fixed
 +    - You will then need to setup the endpoint to take traffic with another az command. Without this you will get an error saying it can't accept requests.
 +      - i.e. az ml online-endpoint update --workspace don-ml-workspace-fixed --name collectibles-endpoint-11ee416b --resource-group don-test-rg-SCUS --traffic blue=100
 +  - What is in the score.py to define what data format is in use has to match the test script, which ChatGPT had a hard time with.
 +  - You have to be on nothing newer than Python3.9 due to incompatibilities with anything newer.
 +  - On Macs you have a controlled Python install if you've done it through homebrew so you need to install and use pihpx to create the venv to use for this install/scripts.
 +    - pipx install requests
 +    - pipx inject requests azure-ai-textanalytics azure-core opencensus-ext-azure opencensus-ext-requests opencensus azure-cognitiveservices-speech openai opencensus-ext-azure fastapi uvicorn joblib scikit-learn pandas --include-deps
 +      - This will put all the modules in the same directory so you won't have to mess with missing modules.
 +      - You would use /Users/<username>/.local/pipx/venvs/requests/bin/python3.9 for the environment line on your python scripts
 +        - This would be the first line (#!/Users/<username>/.local/pipx/venvs/requests/bin/python3.9)
 +
 +===== Transcript of steps taken to make AI create scripts =====
 +
  
 In **Azure Machine Learning (Azure ML)**, datasets used for training can be in a variety of formats. The platform is flexible, but depending on how you plan to use the dataset (e.g., for AutoML, custom training, or pipelines), certain formats are more appropriate. In **Azure Machine Learning (Azure ML)**, datasets used for training can be in a variety of formats. The platform is flexible, but depending on how you plan to use the dataset (e.g., for AutoML, custom training, or pipelines), certain formats are more appropriate.
  
-==== ✅ Commonly Supported Formats ====+=== ✅ Commonly Supported Formats ===
  
 ^ Format ^ Description ^ Notes ^ ^ Format ^ Description ^ Notes ^
Line 28: Line 277:
 ---- ----
  
-==== ✅ Where to Store ====+=== ✅ Where to Store ===
  
 Datasets must be accessible to Azure ML compute. Typical storage options: Datasets must be accessible to Azure ML compute. Typical storage options:
Line 65: Line 314:
 ---- ----
  
-==== ✅ Option 1: Export a Table to CSV Using SQL (INTO OUTFILE) ====+=== ✅ Option 1: Export a Table to CSV Using SQL (INTO OUTFILE) ===
  
 <code -> <code ->
Line 84: Line 333:
 ---- ----
  
-==== ✅ Option 2: Use mysql CLI and sed/awk (CSV-like output) ====+=== ✅ Option 2: Use mysql CLI and sed/awk (CSV-like output) ===
  
 <code -> <code ->
Line 95: Line 344:
 ---- ----
  
-==== ✅ Option 3: Python Script to Dump Entire Database to CSV Files (per Table) ====+=== ✅ Option 3: Python Script to Dump Entire Database to CSV Files (per Table) ===
  
 If you want a full database export (one CSV per table): If you want a full database export (one CSV per table):
Line 120: Line 369:
 ---- ----
  
-==== 🔐 Permissions Reminder ====+=== 🔐 Permissions Reminder ===
  
 If you're getting errors with ''INTO OUTFILE'', check: If you're getting errors with ''INTO OUTFILE'', check:
Line 143: Line 392:
 ---- ----
  
-===== ✅ 1. Via Azure ML Studio (Web UI) =====+=== ✅ 1. Via Azure ML Studio (Web UI) ===
  
-==== 📍 Steps: ====+== 📍 Steps: ==
  
   - Go to Azure ML Studio   - Go to Azure ML Studio
Line 160: Line 409:
 ---- ----
  
-===== ✅ 2. Via Python SDK =====+=== ✅ 2. Via Python SDK ===
  
-==== 🔧 Example: Upload a CSV as a tabular dataset ====+== 🔧 Example: Upload a CSV as a tabular dataset ==
  
 <code -> <code ->
Line 193: Line 442:
 ---- ----
  
-===== ✅ 3. Via Azure CLI =====+=== ✅ 3. Via Azure CLI ===
  
 <code -> <code ->
Line 207: Line 456:
 ---- ----
  
-===== ✅ 4. From Azure Blob Storage or External URL =====+=== ✅ 4. From Azure Blob Storage or External URL ===
  
 If your data is already in Azure Blob: If your data is already in Azure Blob:
Line 229: Line 478:
 ---- ----
  
-===== 🔄 Upload Types =====+=== 🔄 Upload Types ===
  
 ^ Type ^ Use Case ^ ^ Type ^ Use Case ^
Line 259: Line 508:
 ---- ----
  
-===== ✅ Goal =====+=== ✅ Goal ===
  
 You want to **input a character name** and retrieve **associated details** from your dataset. This suggests: You want to **input a character name** and retrieve **associated details** from your dataset. This suggests:
Line 268: Line 517:
 ---- ----
  
-===== ✅ Step-by-Step Plan (Using Azure ML + OpenAI or Embeddings) =====+=== ✅ Step-by-Step Plan (Using Azure ML + OpenAI or Embeddings) ===
  
-==== Step 1: Understand Your Data ====+== Step 1: Understand Your Data ==
  
 I'll examine your dataset. I'll examine your dataset.
Line 286: Line 535:
 ---- ----
  
-===== ✅ ML-Based Query System Options =====+=== ✅ ML-Based Query System Options ===
  
 Since you're aiming to **query by character** and get full details, you have two main paths: Since you're aiming to **query by character** and get full details, you have two main paths:
Line 292: Line 541:
 ---- ----
  
-==== 🔹 Option 1: Traditional Filter-Based Query ====+== 🔹 Option 1: Traditional Filter-Based Query ==
  
 No ML needed — just build a UI or API to filter rows where ''character = input''. No ML needed — just build a UI or API to filter rows where ''character = input''.
Line 300: Line 549:
 ---- ----
  
-==== 🔹 Option 2: AI-Powered Search (Semantic or Fuzzy Matching) ====+== 🔹 Option 2: AI-Powered Search (Semantic or Fuzzy Matching) ==
  
 Use **OpenAI embeddings** + **Azure ML** to let the user type: Use **OpenAI embeddings** + **Azure ML** to let the user type:
Line 308: Line 557:
 **Steps:** **Steps:**
  
-=== Step 1: Generate Embeddings for Each Row ===+= Step 1: Generate Embeddings for Each Row =
  
 Use OpenAI's ''text-embedding-ada-002'' or Azure OpenAI equivalent on a string like: Use OpenAI's ''text-embedding-ada-002'' or Azure OpenAI equivalent on a string like:
Line 322: Line 571:
 ---- ----
  
-===== ✅ Recommendation =====+=== ✅ Recommendation ===
  
 Would you prefer: Would you prefer:
Line 332: Line 581:
 I can generate code or deploy scripts for either path. Which would you like? I can generate code or deploy scripts for either path. Which would you like?
  
-== You said: ==+= You said: =
  
 I would like to us ML for this. Do you have suggestions for some example that would be more suited to using ML with this dataset? I would like to us ML for this. Do you have suggestions for some example that would be more suited to using ML with this dataset?
Line 344: Line 593:
 ---- ----
  
-===== ✅ 1. Price Estimation (Regression) =====+=== ✅ 1. Price Estimation (Regression) ===
  
-==== 📌 Problem: ====+== 📌 Problem: ==
  
 Predict ''approximate_value'' based on other fields (''character'', ''type'', ''manufacturer'', ''list_price'', etc.). Predict ''approximate_value'' based on other fields (''character'', ''type'', ''manufacturer'', ''list_price'', etc.).
  
-==== ✅ Why it fits: ====+== ✅ Why it fits: ==
  
   * You have labeled numeric data.   * You have labeled numeric data.
   * It's useful for appraising unlisted items.   * It's useful for appraising unlisted items.
  
-==== 🔧 ML Type: ====+== 🔧 ML Type: ==
  
   * **Regression** (e.g., Linear Regression, XGBoost, AutoML)   * **Regression** (e.g., Linear Regression, XGBoost, AutoML)
Line 361: Line 610:
 ---- ----
  
-===== ✅ 2. Category Prediction (Classification) =====+=== ✅ 2. Category Prediction (Classification) ===
  
-==== 📌 Problem: ====+== 📌 Problem: ==
  
 Predict the ''type'' of collectible or its ''location'' based on fields like ''character'', ''property'', and ''manufacturer''. Predict the ''type'' of collectible or its ''location'' based on fields like ''character'', ''property'', and ''manufacturer''.
  
-==== ✅ Why it fits: ====+== ✅ Why it fits: ==
  
   * Helps auto-label new entries.   * Helps auto-label new entries.
   * Enables predictive organization/sorting.   * Enables predictive organization/sorting.
  
-==== 🔧 ML Type: ====+== 🔧 ML Type: ==
  
   * **Classification**   * **Classification**
Line 378: Line 627:
 ---- ----
  
-===== ✅ 3. Clustering Characters by Similarity (Unsupervised) =====+=== ✅ 3. Clustering Characters by Similarity (Unsupervised) ===
  
-==== 📌 Problem: ====+== 📌 Problem: ==
  
 Group similar characters or figures automatically to find patterns or suggest groupings. Group similar characters or figures automatically to find patterns or suggest groupings.
  
-==== ✅ Why it fits: ====+== ✅ Why it fits: ==
  
   * Explores hidden structure.   * Explores hidden structure.
   * Could be visualized or used to build recommendation systems.   * Could be visualized or used to build recommendation systems.
  
-==== 🔧 ML Type: ====+== 🔧 ML Type: ==
  
   * **Clustering (e.g., KMeans)** using embeddings of text descriptions.   * **Clustering (e.g., KMeans)** using embeddings of text descriptions.
Line 395: Line 644:
 ---- ----
  
-===== ✅ 4. Anomaly Detection =====+=== ✅ 4. Anomaly Detection ===
  
-==== 📌 Problem: ====+== 📌 Problem: ==
  
 Find collectibles that are priced much higher/lower than similar items. Find collectibles that are priced much higher/lower than similar items.
  
-==== ✅ Why it fits: ====+== ✅ Why it fits: ==
  
   * Helps find mispriced entries or rare items.   * Helps find mispriced entries or rare items.
  
-==== 🔧 ML Type: ====+== 🔧 ML Type: ==
  
   * **Anomaly Detection (Isolation Forest, One-Class SVM)**   * **Anomaly Detection (Isolation Forest, One-Class SVM)**
Line 411: Line 660:
 ---- ----
  
-===== ✅ 5. Embedding-Based Semantic Search (LLM-enhanced ML) =====+=== ✅ 5. Embedding-Based Semantic Search (LLM-enhanced ML) ===
  
-==== 📌 Problem: ====+== 📌 Problem: ==
  
 Let users search using natural language and get intelligent matches. Let users search using natural language and get intelligent matches.
  
-==== ✅ Why it fits: ====+== ✅ Why it fits: ==
  
   * Transforms character/item descriptions into embeddings.   * Transforms character/item descriptions into embeddings.
   * Allows vector similarity search over the dataset.   * Allows vector similarity search over the dataset.
  
-==== 🔧 Tools: ====+== 🔧 Tools: ==
  
   * Azure OpenAI (for embeddings)   * Azure OpenAI (for embeddings)
Line 430: Line 679:
 ---- ----
  
-===== 🧠 Suggestion =====+=== 🧠 Suggestion ===
  
 To get started with a real ML training task: To get started with a real ML training task:
  
-==== ▶️ Start with Price Estimation using Regression: ====+== ▶️ Start with Price Estimation using Regression: ==
  
   * **Input**: ''character'', ''figure_name'', ''property'', ''type'', ''manufacturer'', ''list_price'', etc.   * **Input**: ''character'', ''figure_name'', ''property'', ''type'', ''manufacturer'', ''list_price'', etc.
Line 441: Line 690:
 Would you like me to generate a full training script (e.g., in Python with scikit-learn or in Azure ML SDK) for this? Would you like me to generate a full training script (e.g., in Python with scikit-learn or in Azure ML SDK) for this?
  
-== You said: ==+= You said: =
  
 Yes Yes
Line 449: Line 698:
 Your regression model has been successfully trained to predict ''approximate_value'' using collectible attributes. The evaluation shows: Your regression model has been successfully trained to predict ''approximate_value'' using collectible attributes. The evaluation shows:
  
-==== ✅ Root Mean Squared Error (RMSE): ~30.15 ====+== ✅ Root Mean Squared Error (RMSE): ~30.15 ==
  
 This means that, on average, the model's predictions are off by about **$30** — not bad for a first pass, considering potential variance in collectible values. This means that, on average, the model's predictions are off by about **$30** — not bad for a first pass, considering potential variance in collectible values.
Line 455: Line 704:
 ---- ----
  
-===== 🧪 Next Steps You Can Take =====+=== 🧪 Next Steps You Can Take ===
  
-==== 🔧 Improvements ====+== 🔧 Improvements ==
  
   * Use more advanced models (e.g., **XGBoost**, **LightGBM**).   * Use more advanced models (e.g., **XGBoost**, **LightGBM**).
Line 3332: Line 3581:
 <code -> <code ->
 bashCopyEditpython score.py bashCopyEditpython score.py
- 
 </code> </code>
  
Line 3343: Line 3591:
     with open(model_path, "rb") as f:     with open(model_path, "rb") as f:
         model = pickle.load(f)         model = pickle.load(f)
- 
 </code> </code>
  
Line 3356: Line 3603:
 with open("collectibles_model.pkl", "wb") as f: with open("collectibles_model.pkl", "wb") as f:
     pickle.dump(model, f)     pickle.dump(model, f)
- 
 </code> </code>
  
Line 3375: Line 3621:
       - numpy       - numpy
       - azureml-inference-server-http       - azureml-inference-server-http
- 
 </code> </code>
  
Line 3388: Line 3633:
 <code -> <code ->
 bashCopyEditAZUREML_MODEL_DIR=. python score.py bashCopyEditAZUREML_MODEL_DIR=. python score.py
- 
 </code> </code>
  
Line 3409: Line 3653:
 ... ...
 model_path = Model.get_model_path("collectibles_model") model_path = Model.get_model_path("collectibles_model")
- 
 </code> </code>
  
Line 3429: Line 3672:
     with open(model_path, "rb") as f:     with open(model_path, "rb") as f:
         model = pickle.load(f)         model = pickle.load(f)
- 
 </code> </code>
  
Line 3448: Line 3690:
   - pip:   - pip:
     - azureml-inference-server-http     - azureml-inference-server-http
- 
 </code> </code>
  
Line 3469: Line 3710:
   - pip:   - pip:
     - azureml-inference-server-http     - azureml-inference-server-http
- 
 </code> </code>
  
Line 3512: Line 3752:
 <code -> <code ->
 jsonCopyEdit{"error": "list indices must be integers or slices, not str"} jsonCopyEdit{"error": "list indices must be integers or slices, not str"}
- 
 </code> </code>
  
Line 3541: Line 3780:
     except Exception as e:     except Exception as e:
         return {"error": str(e)}         return {"error": str(e)}
- 
 </code> </code>
  
Line 3553: Line 3791:
   ...   ...
 } }
- 
 </code> </code>
  
Line 3573: Line 3810:
     except Exception as e:     except Exception as e:
         return {"error": str(e)}         return {"error": str(e)}
- 
 </code> </code>
  
Line 3595: Line 3831:
     "location": "Shelf A"     "location": "Shelf A"
 } }
- 
 </code> </code>
  
Line 3644: Line 3879:
   --workspace-name don-ml-workspace-fixed \   --workspace-name don-ml-workspace-fixed \
   --resource-group don-test-rg-SCUS   --resource-group don-test-rg-SCUS
- 
 </code> </code>
   - **Common issues include:**   - **Common issues include:**
Line 3659: Line 3893:
 <code -> <code ->
 vbnetCopyEditModuleNotFoundError: No module named 'numpy._core' vbnetCopyEditModuleNotFoundError: No module named 'numpy._core'
- 
 </code> </code>
  
Line 3670: Line 3903:
 <code -> <code ->
 pgsqlCopyEditInconsistentVersionWarning: Trying to unpickle estimator OneHotEncoder from version 1.6.1 when using version 1.3.2. pgsqlCopyEditInconsistentVersionWarning: Trying to unpickle estimator OneHotEncoder from version 1.6.1 when using version 1.3.2.
- 
 </code> </code>
  
Line 3697: Line 3929:
       - joblib       - joblib
       - azureml-inference-server-http       - azureml-inference-server-http
- 
 </code> </code>
  
Line 3722: Line 3953:
  
 Would you like me to regenerate and send back a corrected ''env.yml'' and ZIP package for redeployment with these fixes? Would you like me to regenerate and send back a corrected ''env.yml'' and ZIP package for redeployment with these fixes?
 +
 +This went on for another 2 hours of pain.  It got into a loop of giving me the same answer over and over.  Do this, not do this, no do the first thing, no the second thing.  Had to tell it to reset itself to the current files and only use them instead of past questions/data.  Finally got a working model.
 +
 +
 +[[ai_knowledge|AI Knowledge]]
  
  
wiki/ai/cli-workspace-deployment-upload.1748985585.txt.gz · Last modified: by ddehamer

Page Tools

Trace:
Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki

Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com) IP:10.0.136.41