Update legacy models across non-legacy cookbooks

Author: ashprabaker

capabilities/classification/evaluation/promptfooconfig.yaml

@@ -7,27 +7,27 @@ prompts:
   - prompts.py:rag_chain_of_thought_classify
 
 providers:
-  - id: anthropic:messages:claude-3-haiku-20240307
+  - id: anthropic:messages:claude-haiku-4-5
     label: "Haiku: T-0.0"
     config:
       max_tokens: 4096
       temperature: 0
-  - id: anthropic:messages:claude-3-haiku-20240307
+  - id: anthropic:messages:claude-haiku-4-5
     label: "Haiku: T-0.2"
     config:
       max_tokens: 4096
       temperature: 0.2
-  - id: anthropic:messages:claude-3-haiku-20240307
+  - id: anthropic:messages:claude-haiku-4-5
     label: "Haiku: T-0.4"
     config:
       max_tokens: 4096
       temperature: 0.4
-  - id: anthropic:messages:claude-3-haiku-20240307
+  - id: anthropic:messages:claude-haiku-4-5
     label: "Haiku: T-0.6"
     config:
       max_tokens: 4096
       temperature: 0.6
-  - id: anthropic:messages:claude-3-haiku-20240307
+  - id: anthropic:messages:claude-haiku-4-5
     label: "Haiku: T-0.8"
     config:
       max_tokens: 4096

capabilities/classification/guide.ipynb

@@ -490,7 +490,7 @@
     "        stop_sequences=[\"</category>\"], \n",
     "        max_tokens=4096, \n",
     "        temperature=0.0,\n",
-    "        model=\"claude-3-haiku-20240307\"\n",
+    "        model=\"claude-haiku-4-5\"\n",
     "    )\n",
     "    \n",
     "    # Extract the result from the response\n",
@@ -734,7 +734,7 @@
     "        stop_sequences=[\"</category>\"], \n",
     "        max_tokens=4096, \n",
     "        temperature=0.0,\n",
-    "        model=\"claude-3-haiku-20240307\"\n",
+    "        model=\"claude-haiku-4-5\"\n",
     "    )\n",
     "    \n",
     "    # Extract the result from the response\n",
@@ -846,7 +846,7 @@
     "        stop_sequences=[\"</category>\"], \n",
     "        max_tokens=4096, \n",
     "        temperature=0.0,\n",
-    "        model=\"claude-3-haiku-20240307\"\n",
+    "        model=\"claude-haiku-4-5\"\n",
     "    )\n",
     "    \n",
     "    # Extract the result from the response\n",

capabilities/contextual-embeddings/guide.ipynb

@@ -35,7 +35,7 @@ def evaluate_end_to_end(query, generated_answer, correct_answer):
     client = Anthropic(api_key=os.environ.get('ANTHROPIC_API_KEY'))
     try:
         response = client.messages.create(
-            model="claude-3-5-sonnet-20241022",
+            model="claude-sonnet-4-5",
             max_tokens=1500,
             messages=[
                 {"role": "user", "content": prompt},

capabilities/retrieval_augmented_generation/evaluation/eval_end_to_end.py

@@ -7,13 +7,13 @@ prompts:
   - prompts.py:answer_query_level_three
 
 providers:
-  - id: anthropic:messages:claude-3-haiku-20240307
+  - id: anthropic:messages:claude-haiku-4-5
     label: "Haiku: T-0.0"
     config:
       max_tokens: 2500
       temperature: 0
 
-  - id: anthropic:messages:claude-3-5-sonnet-20241022
+  - id: anthropic:messages:claude-sonnet-4-5
     label: "3.5 Sonnet: T-0.0"
     config:
       max_tokens: 2500

capabilities/retrieval_augmented_generation/evaluation/promptfooconfig_end_to_end.yaml

@@ -106,7 +106,7 @@ def _rerank_results(query: str, results: List[Dict], k: int = 5) -> List[Dict]:
     """
     try:
         response = client.messages.create(
-            model="claude-3-haiku-20240307",
+            model="claude-haiku-4-5",
             max_tokens=50,
             messages=[{"role": "user", "content": prompt}, {"role": "assistant", "content": "<relevant_indices>"}],
             temperature=0,

capabilities/retrieval_augmented_generation/evaluation/prompts.py

@@ -67,7 +67,7 @@ def _rerank_results(query: str, results: List[Dict], k: int = 3) -> List[Dict]:
     client = Anthropic(api_key=os.environ.get('ANTHROPIC_API_KEY'))
     try:
         response = client.messages.create(
-            model="claude-3-5-sonnet-20241022",
+            model="claude-sonnet-4-5",
             max_tokens=50,
             messages=[{"role": "user", "content": prompt}, {"role": "assistant", "content": "<relevant_indices>"}],
             temperature=0,

capabilities/retrieval_augmented_generation/evaluation/provider_retrieval.py

@@ -360,7 +360,7 @@
     "    Answer the question now, and avoid providing preamble such as 'Here is the answer', etc\n",
     "    \"\"\"\n",
     "    response = client.messages.create(\n",
-    "        model=\"claude-3-haiku-20240307\",\n",
+    "        model=\"claude-haiku-4-5\",\n",
     "        max_tokens=2500,\n",
     "        messages=[\n",
     "            {\"role\": \"user\", \"content\": prompt}\n",
@@ -643,7 +643,7 @@
     "        \n",
     "        try:\n",
     "            response = client.messages.create(\n",
-    "                model=\"claude-3-5-sonnet-20241022\",\n",
+    "                model=\"claude-sonnet-4-5\",\n",
     "                max_tokens=1500,\n",
     "                messages=[\n",
     "                    {\"role\": \"user\", \"content\": prompt},\n",
@@ -3264,7 +3264,7 @@
     "        \"\"\"\n",
     "\n",
     "        response = client.messages.create(\n",
-    "            model=\"claude-3-haiku-20240307\",\n",
+    "            model=\"claude-haiku-4-5\",\n",
     "            max_tokens=150,\n",
     "            messages=[\n",
     "                {\"role\": \"user\", \"content\": prompt}\n",
@@ -3461,7 +3461,7 @@
     "    Answer the question now, and avoid providing preamble such as 'Here is the answer', etc\n",
     "    \"\"\"\n",
     "    response = client.messages.create(\n",
-    "        model=\"claude-3-haiku-20240307\",\n",
+    "        model=\"claude-haiku-4-5\",\n",
     "        max_tokens=2500,\n",
     "        messages=[\n",
     "            {\"role\": \"user\", \"content\": prompt}\n",
@@ -5975,7 +5975,7 @@
     "    \"\"\"\n",
     "    try:\n",
     "        response = client.messages.create(\n",
-    "            model=\"claude-3-haiku-20240307\",\n",
+    "            model=\"claude-haiku-4-5\",\n",
     "            max_tokens=50,\n",
     "            messages=[{\"role\": \"user\", \"content\": prompt}, {\"role\": \"assistant\", \"content\": \"<relevant_indices>\"}],\n",
     "            temperature=0,\n",
@@ -6044,7 +6044,7 @@
     "    Answer the question now, and avoid providing preamble such as 'Here is the answer', etc\n",
     "    \"\"\"\n",
     "    response = client.messages.create(\n",
-    "        model=\"claude-3-haiku-20240307\",\n",
+    "        model=\"claude-haiku-4-5\",\n",
     "        max_tokens=2500,\n",
     "        messages=[{\"role\": \"user\", \"content\": prompt}],\n",
     "        temperature=0\n",

capabilities/retrieval_augmented_generation/guide.ipynb

@@ -53,7 +53,7 @@ def llm_eval(summary, input):
     Evaluation (JSON format):"""
 
     response = client.messages.create(
-        model="claude-3-5-sonnet-20241022",
+        model="claude-sonnet-4-5",
         max_tokens=1000,
         temperature=0,
         messages=[

capabilities/summarization/evaluation/custom_evals/llm_eval.py

@@ -6,12 +6,12 @@ prompts:
   - prompts.py:summarize_long_document
 
 providers:
-  - id: anthropic:messages:claude-3-haiku-20240307
+  - id: anthropic:messages:claude-haiku-4-5
     label: "3.0 Haiku"
     config:
       max_tokens: 4096
       temperature: 0
-  - id: anthropic:messages:claude-3-5-sonnet-20241022
+  - id: anthropic:messages:claude-sonnet-4-5
     label: "3.5 Sonnet"
     config:
       max_tokens: 4096