Adapt to New inference backend config (#48)

- Bump `pipelex` to `v0.10.2`: See `Pipelex` changelog [here](https://docs.pipelex.com/changelog/)

Author: lchoquel

.pipelex/inference/backends.toml

@@ -0,0 +1,50 @@
+[pipelex_inference]
+endpoint = "https://inference.pipelex.com/v1"
+api_key = "${PIPELEX_INFERENCE_API_KEY}"
+
+[blackboxai]
+enabled = true
+endpoint = "https://api.blackbox.ai/v1"
+api_key = "${BLACKBOX_API_KEY}"
+
+[openai]
+enabled = true
+api_key = "${OPENAI_API_KEY}"
+
+[azure_openai]
+enabled = true
+endpoint = "${AZURE_API_BASE}"
+api_key = "${AZURE_API_KEY}"
+api_version = "${AZURE_API_VERSION}"
+
+[anthropic]
+enabled = true
+api_key = "${ANTHROPIC_API_KEY}"
+claude_4_tokens_limit = 8192
+
+[ollama]
+enabled = true
+endpoint = "http://localhost:11434/v1"
+
+[xai]
+enabled = true
+endpoint = "https://api.x.ai/v1"
+api_key = "${XAI_API_KEY}"
+
+[bedrock]
+enabled = true
+aws_region = "${AWS_REGION}"
+
+[vertexai]
+enabled = true
+gcp_project_id = "${GCP_PROJECT_ID}"
+gcp_location = "${GCP_LOCATION}"
+gcp_credentials_file_path = "${GCP_CREDENTIALS_FILE_PATH}"
+
+[mistral]
+enabled = true
+api_key = "${MISTRAL_API_KEY}"
+
+[internal] # software-only backend, runs internally, without AI
+enabled = true
+

.pipelex/inference/backends/anthropic.toml

@@ -0,0 +1,67 @@
+default_sdk = "anthropic"
+default_prompting_target = "anthropic"
+
+[claude-3-haiku]
+model_id = "claude-3-haiku-20240307"
+max_tokens = 4096
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 0.25, output = 1.25 }
+
+[claude-3-opus]
+model_id = "claude-3-opus-20240229"
+max_tokens = 4096
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 15.0, output = 75.0 }
+
+["claude-3.5-sonnet"]
+model_id = "claude-3-5-sonnet-20240620"
+max_tokens = 8192
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+["claude-3.5-sonnet-v2"]
+model_id = "claude-3-5-sonnet-20241022"
+max_tokens = 8192
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+["claude-3.7-sonnet"]
+model_id = "claude-3-7-sonnet-20250219"
+max_tokens = 8192
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+[claude-4-sonnet]
+model_id = "claude-sonnet-4-20250514"
+max_tokens = 64000
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+[claude-4-opus]
+model_id = "claude-opus-4-20250514"
+max_tokens = 32000
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+["claude-4.1-opus"]
+model_id = "claude-opus-4-1-20250805"
+max_tokens = 32000
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+

.pipelex/inference/backends/azure_openai.toml

@@ -0,0 +1,69 @@
+default_sdk = "azure_openai"
+default_prompting_target = "openai"
+
+[gpt-4o]
+model_id = "gpt-4o-2024-11-20"
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+costs = { input = 2.5, output = 10.0 }
+
+[gpt-4o-mini]
+model_id = "gpt-4o-mini-2024-07-18"
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+costs = { input = 0.15, output = 0.6 }
+
+["gpt-4.1"]
+model_id = "gpt-4.1-2025-04-14"
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+costs = { input = 2, output = 8 }
+
+["gpt-4.1-mini"]
+model_id = "gpt-4.1-mini-2025-04-14"
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+costs = { input = 0.4, output = 1.6 }
+
+["gpt-4.1-nano"]
+model_id = "gpt-4.1-nano-2025-04-14"
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+costs = { input = 0.1, output = 0.4 }
+
+[o1-mini]
+model_id = "o1-mini-2024-09-12"
+inputs = ["text"]
+outputs = ["text", "structured"]
+costs = { input = 3.0, output = 12.0 }
+
+[o1]
+model_id = "o1-2024-12-17"
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+costs = { input = 15.0, output = 60.0 }
+
+[o3-mini]
+model_id = "o3-mini-2025-01-31"
+inputs = ["text"]
+outputs = ["text", "structured"]
+costs = { input = 1.1, output = 4.4 }
+
+[gpt-5-mini]
+model_id = "gpt-5-mini-2025-08-07"
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+costs = { input = 0.25, output = 2.0 }
+
+[gpt-5-nano]
+model_id = "gpt-5-nano-2025-08-07"
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+costs = { input = 0.05, output = 0.4 }
+
+[gpt-5-chat]
+model_id = "gpt-5-chat-2025-08-07"
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+costs = { input = 1.25, output = 10.0 }
+

.pipelex/inference/backends/bedrock.toml

@@ -0,0 +1,84 @@
+default_sdk = "bedrock_aioboto3"
+default_prompting_target = "anthropic"
+
+[bedrock-mistral-large]
+model_id = "mistral.mistral-large-2407-v1:0"
+max_tokens = 8192
+inputs = ["text"]
+outputs = ["text"]
+costs = { input = 4.0, output = 12.0 }
+
+[bedrock-meta-llama-3-3-70b-instruct]
+model_id = "us.meta.llama3-3-70b-instruct-v1:0"
+max_tokens = 8192
+inputs = ["text"]
+outputs = ["text"]
+# TODO: find out the actual cost per million tokens for llama3 on bedrock
+costs = { input = 3.0, output = 15.0 }
+
+[bedrock-nova-pro]
+model_id = "us.amazon.nova-pro-v1:0"
+max_tokens = 5120
+inputs = ["text"]
+outputs = ["text"]
+# TODO: find out the actual cost per million tokens for nova on bedrock
+costs = { input = 3.0, output = 15.0 }
+
+################################################################################
+# Anthropic Models
+################################################################################
+
+["claude-3.5-sonnet"]
+sdk = "bedrock_anthropic"
+model_id = "us.anthropic.claude-3-5-sonnet-20240620-v1:0"
+max_tokens = 8192
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+["claude-3.5-sonnet-v2"]
+sdk = "bedrock_anthropic"
+model_id = "anthropic.claude-3-5-sonnet-20241022-v2:0"
+max_tokens = 8192
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+["claude-3.7-sonnet"]
+sdk = "bedrock_anthropic"
+model_id = "us.anthropic.claude-3-7-sonnet-20250219-v1:0"
+max_tokens = 8192
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+[claude-4-sonnet]
+sdk = "bedrock_anthropic"
+model_id = "us.anthropic.claude-sonnet-4-20250514-v1:0"
+max_tokens = 64000
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+[claude-4-opus]
+sdk = "bedrock_anthropic"
+model_id = "us.anthropic.claude-opus-4-20250514-v1:0"
+max_tokens = 32000
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+
+["claude-4.1-opus"]
+sdk = "bedrock_anthropic"
+model_id = "us.anthropic.claude-opus-4-1-20250805-v1:0"
+max_tokens = 32000
+inputs = ["text", "images"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 3.0, output = 15.0 }
+