|
|
@ -33,17 +33,17 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 8191
|
|
|
|
max_input_tokens: 8191
|
|
|
|
default_chunk_size: 3000
|
|
|
|
default_chunk_size: 3000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: text-embedding-3-small
|
|
|
|
- name: text-embedding-3-small
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 8191
|
|
|
|
max_input_tokens: 8191
|
|
|
|
default_chunk_size: 3000
|
|
|
|
default_chunk_size: 3000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: text-embedding-ada-002
|
|
|
|
- name: text-embedding-ada-002
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 8191
|
|
|
|
max_input_tokens: 8191
|
|
|
|
default_chunk_size: 3000
|
|
|
|
default_chunk_size: 3000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
|
|
|
|
|
|
|
|
- platform: gemini
|
|
|
|
- platform: gemini
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -77,7 +77,7 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 2048
|
|
|
|
max_input_tokens: 2048
|
|
|
|
default_chunk_size: 1500
|
|
|
|
default_chunk_size: 1500
|
|
|
|
max_concurrent_chunks: 5
|
|
|
|
max_batch_size: 5
|
|
|
|
|
|
|
|
|
|
|
|
- platform: claude
|
|
|
|
- platform: claude
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -176,12 +176,12 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 96
|
|
|
|
max_batch_size: 96
|
|
|
|
- name: embed-multilingual-v3.0
|
|
|
|
- name: embed-multilingual-v3.0
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 96
|
|
|
|
max_batch_size: 96
|
|
|
|
- name: rerank-english-v3.0
|
|
|
|
- name: rerank-english-v3.0
|
|
|
|
type: rerank
|
|
|
|
type: rerank
|
|
|
|
max_input_tokens: 4096
|
|
|
|
max_input_tokens: 4096
|
|
|
@ -307,12 +307,12 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 3072
|
|
|
|
max_input_tokens: 3072
|
|
|
|
default_chunk_size: 2000
|
|
|
|
default_chunk_size: 2000
|
|
|
|
max_concurrent_chunks: 5
|
|
|
|
max_batch_size: 5
|
|
|
|
- name: text-multilingual-embedding-002
|
|
|
|
- name: text-multilingual-embedding-002
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 3072
|
|
|
|
max_input_tokens: 3072
|
|
|
|
default_chunk_size: 2000
|
|
|
|
default_chunk_size: 2000
|
|
|
|
max_concurrent_chunks: 5
|
|
|
|
max_batch_size: 5
|
|
|
|
|
|
|
|
|
|
|
|
- platform: vertexai-claude
|
|
|
|
- platform: vertexai-claude
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -460,12 +460,12 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: '@cf/baai/bge-large-en-v1.5'
|
|
|
|
- name: '@cf/baai/bge-large-en-v1.5'
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
|
|
|
|
|
|
|
|
- platform: replicate
|
|
|
|
- platform: replicate
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -578,7 +578,7 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 2048
|
|
|
|
max_input_tokens: 2048
|
|
|
|
default_chunk_size: 1500
|
|
|
|
default_chunk_size: 1500
|
|
|
|
max_concurrent_chunks: 25
|
|
|
|
max_batch_size: 25
|
|
|
|
|
|
|
|
|
|
|
|
- platform: moonshot
|
|
|
|
- platform: moonshot
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -721,12 +721,12 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 30
|
|
|
|
max_batch_size: 30
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 30
|
|
|
|
max_batch_size: 30
|
|
|
|
|
|
|
|
|
|
|
|
- platform: deepinfra
|
|
|
|
- platform: deepinfra
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -773,52 +773,52 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: BAAI/bge-base-en-v1.5
|
|
|
|
- name: BAAI/bge-base-en-v1.5
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: BAAI/bge-m3
|
|
|
|
- name: BAAI/bge-m3
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 8192
|
|
|
|
max_input_tokens: 8192
|
|
|
|
default_chunk_size: 2000
|
|
|
|
default_chunk_size: 2000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: intfloat/e5-base-v2
|
|
|
|
- name: intfloat/e5-base-v2
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: intfloat/e5-large-v2
|
|
|
|
- name: intfloat/e5-large-v2
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: intfloat/multilingual-e5-large
|
|
|
|
- name: intfloat/multilingual-e5-large
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: sentence-transformers/all-MiniLM-L6-v2
|
|
|
|
- name: sentence-transformers/all-MiniLM-L6-v2
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: sentence-transformers/paraphrase-MiniLM-L6-v2
|
|
|
|
- name: sentence-transformers/paraphrase-MiniLM-L6-v2
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: thenlper/gte-base
|
|
|
|
- name: thenlper/gte-base
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
|
|
|
|
|
|
|
|
- platform: fireworks
|
|
|
|
- platform: fireworks
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -876,22 +876,22 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 8192
|
|
|
|
max_input_tokens: 8192
|
|
|
|
default_chunk_size: 1500
|
|
|
|
default_chunk_size: 1500
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: WhereIsAI/UAE-Large-V1
|
|
|
|
- name: WhereIsAI/UAE-Large-V1
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: thenlper/gte-base
|
|
|
|
- name: thenlper/gte-base
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
|
|
|
|
|
|
|
|
- platform: openrouter
|
|
|
|
- platform: openrouter
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -1072,7 +1072,7 @@
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
|
|
|
|
|
|
|
|
- platform: together
|
|
|
|
- platform: together
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -1108,19 +1108,19 @@
|
|
|
|
max_input_tokens: 32768
|
|
|
|
max_input_tokens: 32768
|
|
|
|
input_price: 0.9
|
|
|
|
input_price: 0.9
|
|
|
|
output_price: 0.9
|
|
|
|
output_price: 0.9
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: WhereIsAI/UAE-Large-V1
|
|
|
|
- name: WhereIsAI/UAE-Large-V1
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: BAAI/bge-large-en-v1.5
|
|
|
|
- name: BAAI/bge-large-en-v1.5
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|
|
|
|
- name: BAAI/bge-base-en-v1.5
|
|
|
|
- name: BAAI/bge-base-en-v1.5
|
|
|
|
type: embedding
|
|
|
|
type: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
max_batch_size: 100
|