Migrate some examples from Replicate to Ollama (#522)

* Update examples to use ollama

Signed-off-by: Jing Chen <[email protected]>

* Rever some examples from ollama back to replicate

Signed-off-by: Jing Chen <[email protected]>

* Set ollama granite default temperature to 0


---------

Signed-off-by: Jing Chen <[email protected]>

Author: jgchn

docs/tutorial.md

@@ -653,7 +653,7 @@ This is similar to a spreadsheet for tabular data, where data is in the forefron
 ## Using Ollama models
 
 1. Install Ollama e.g., `brew install --cask ollama`
-2. Run a model e.g., `ollama run granite-code:34b-instruct-q5_K_M`. See [the Ollama library for more models](https://ollama.com/library/granite-code/tags)
+2. Run a model e.g., `ollama run granite-code:8b`. See [the Ollama library for more models](https://ollama.com/library/granite-code/tags)
 3. An OpenAI style server is running locally at [http://localhost:11434/](http://localhost:11434/), see [the Ollama blog](https://ollama.com/blog/openai-compatibility) for more details.
 
 
@@ -662,7 +662,7 @@ Example:
 ```
 text:
 - Hello,
-- model: ollama_chat/granite-code:34b-instruct-q5_K_M
+- model: ollama_chat/granite-code:8b
   parameters:
     stop:
     - '!'

examples/callback/repair_prompt.pdl

@@ -9,7 +9,7 @@ lastOf:
   Please repair the code!
 
 - def: raw_output
-  model: replicate/ibm-granite/granite-3.1-8b-instruct
+  model: ollama/granite-code:8b
   parameters:
     #stop_sequences: "\n\n"
     temperature: 0

examples/chatbot/chatbot.pdl

@@ -6,7 +6,7 @@ text:
 - repeat:
     text:
     # Send context to Granite model hosted at replicate.com
-    - model: replicate/ibm-granite/granite-3.1-8b-instruct
+    - model: ollama/granite-code:8b
     # Allow the user to type 'yes', 'no', or anything else, storing
     # the input into a variable named `eval`.  The input is also implicitly
     # added to the context.

examples/code/code-eval.pdl

@@ -10,13 +10,13 @@ defs:
 text:
 # Print the source code to the console
 - "\n${ CODE.source_code }\n"
-# Use replicate.com to invoke a Granite model with a prompt.  Output AND
+# Use ollama to invoke a Granite model with a prompt.  Output AND
 # set the variable `EXPLANATION` to the output.
-- model: replicate/ibm-granite/granite-3.1-8b-instruct
+- model: ollama/granite-code:8b
   def: EXPLANATION
   input: |
       Here is some info about the location of the function in the repo.
-      repo: 
+      repo:
       ${ CODE.repo_info.repo }
       path: ${ CODE.repo_info.path }
       Function_name: ${ CODE.repo_info.function_name }

examples/code/code-json.pdl

@@ -6,13 +6,13 @@ defs:
   TRUTH:
     read: ./ground_truth.txt
 text:
-- model: replicate/ibm-granite/granite-3.1-8b-instruct
+- model: ollama/granite-code:8b
   def: EXPLANATION
   contribute: []
   input:
      |
       Here is some info about the location of the function in the repo.
-      repo: 
+      repo:
       ${ CODE.repo_info.repo }
       path: ${ CODE.repo_info.path }
       Function_name: ${ CODE.repo_info.function_name }
@@ -37,7 +37,7 @@ text:
     """
     # (In PDL, set `result` to the output you wish for your code block.)
     result = textdistance.levenshtein.normalized_similarity(expl, truth)
-- data: 
+- data:
     input: ${ CODE }
     output: ${ EXPLANATION }
     metric: ${ EVAL }

examples/code/code.pdl

@@ -7,16 +7,16 @@ defs:
 text:
 # Output the `source_code:` of the YAML to the console
 - "\n${ CODE.source_code }\n"
-# Use replicate.com to invoke a Granite model with a prompt
-- model: replicate/ibm-granite/granite-3.1-8b-instruct
+# Use ollama to invoke a Granite model with a prompt
+- model: ollama/granite-code:8b
   input: |
     Here is some info about the location of the function in the repo.
-    repo: 
+    repo:
     ${ CODE.repo_info.repo }
     path: ${ CODE.repo_info.path }
     Function_name: ${ CODE.repo_info.function_name }
 
-    
+
     Explain the following code:
     ```
     ${ CODE.source_code }```

examples/demo/3-weather.pdl

@@ -2,7 +2,7 @@ description: Using a weather API and LLM to make a small weather app
 text:
 - def: QUERY
   text: "What is the weather in Madrid?\n"
-- model: replicate/ibm-granite/granite-3.1-8b-instruct
+- model: ollama/granite-code:8b
   input: |
       Extract the location from the question.
       Question: What is the weather in London?
@@ -19,14 +19,14 @@ text:
 - lang: python
   code: |
     import requests
-    #result = requests.get('https://api.weatherapi.com/v1/current.json?key==XYZ=${ LOCATION }') 
+    #result = requests.get('https://api.weatherapi.com/v1/current.json?key==XYZ=${ LOCATION }')
     #Mock result:
     result = '{"location": {"name": "Madrid", "region": "Madrid", "country": "Spain", "lat": 40.4, "lon": -3.6833, "tz_id": "Europe/Madrid", "localtime_epoch": 1732543839, "localtime": "2024-11-25 15:10"}, "current": {"last_updated_epoch": 1732543200, "last_updated": "2024-11-25 15:00", "temp_c": 14.4, "temp_f": 57.9, "is_day": 1, "condition": {"text": "Partly cloudy", "icon": "//cdn.weatherapi.com/weather/64x64/day/116.png", "code": 1003}, "wind_mph": 13.2, "wind_kph": 21.2, "wind_degree": 265, "wind_dir": "W", "pressure_mb": 1017.0, "pressure_in": 30.03, "precip_mm": 0.01, "precip_in": 0.0, "humidity": 77, "cloud": 75, "feelslike_c": 12.8, "feelslike_f": 55.1, "windchill_c": 13.0, "windchill_f": 55.4, "heatindex_c": 14.5, "heatindex_f": 58.2, "dewpoint_c": 7.3, "dewpoint_f": 45.2, "vis_km": 10.0, "vis_miles": 6.0, "uv": 1.4, "gust_mph": 15.2, "gust_kph": 24.4}}'
   def: WEATHER
   parser: json
   contribute: []
-- model: replicate/ibm-granite/granite-3.1-8b-instruct
+- model: ollama/granite-code:8b
   input: |
       Explain the weather from the following JSON:
       ${ WEATHER }
-  
+

examples/demo/4-translator.pdl

@@ -1,7 +1,7 @@
 description: PDL program
 text:
 - "What is APR?\n"
-- model: replicate/ibm-granite/granite-3.1-8b-instruct
+- model: ollama/granite-code:8b
 - repeat:
     text:
     - read:
@@ -11,5 +11,5 @@ text:
       then:
         text:
         - "\n\nTranslate the above to ${ language }\n"
-        - model: replicate/ibm-granite/granite-3.1-8b-instruct
+        - model: ollama/granite-code:8b
   until: ${ language == 'stop' }

examples/fibonacci/fib.pdl

@@ -6,7 +6,7 @@ text:
 # Use IBM Granite to author a program that computes the Nth Fibonacci number,
 # storing the generated program into the variable `CODE`.
 - def: CODE
-  model: replicate/ibm-granite/granite-3.1-8b-instruct
+  model: ollama/granite-code:8b
   input: "Write a Python function to compute the Fibonacci sequence. Do not include a doc string.\n\n"
   parameters:
     # Request no randomness when generating code
@@ -42,5 +42,4 @@ text:
 
 # Invoke the LLM again to explain the PDL context
 - "\n\nExplain what the above code does and what the result means\n\n"
-- model: replicate/ibm-granite/granite-3.1-8b-instruct
-  
+- model: ollama/granite-code:8b

examples/hello/hello-def-use.pdl

@@ -1,8 +1,8 @@
 description: Hello world with variable use
 text:
 - "Hello\n"
-# Define GEN to be the result of a Granite LLM using replicate.com
-- model: replicate/ibm-granite/granite-3.1-8b-instruct
+# Define GEN to be the result of a Granite LLM using ollama
+- model: ollama/granite-code:8b
   parameters:
     # "greedy" sampling tells the LLM to use the most likely token at each step
     decoding_method: greedy