|
|
@ -77,6 +77,7 @@
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 2048
|
|
|
|
max_input_tokens: 2048
|
|
|
|
default_chunk_size: 1500
|
|
|
|
default_chunk_size: 1500
|
|
|
|
|
|
|
|
max_concurrent_chunks: 5
|
|
|
|
|
|
|
|
|
|
|
|
- platform: claude
|
|
|
|
- platform: claude
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -455,6 +456,16 @@
|
|
|
|
require_max_tokens: true
|
|
|
|
require_max_tokens: true
|
|
|
|
input_price: 0
|
|
|
|
input_price: 0
|
|
|
|
output_price: 0
|
|
|
|
output_price: 0
|
|
|
|
|
|
|
|
- name: '@cf/baai/bge-base-en-v1.5'
|
|
|
|
|
|
|
|
mode: embedding
|
|
|
|
|
|
|
|
max_input_tokens: 512
|
|
|
|
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
|
|
|
|
- name: '@cf/baai/bge-large-en-v1.5'
|
|
|
|
|
|
|
|
mode: embedding
|
|
|
|
|
|
|
|
max_input_tokens: 512
|
|
|
|
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
|
|
|
|
|
|
|
|
- platform: replicate
|
|
|
|
- platform: replicate
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -567,7 +578,7 @@
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 2048
|
|
|
|
max_input_tokens: 2048
|
|
|
|
default_chunk_size: 1500
|
|
|
|
default_chunk_size: 1500
|
|
|
|
max_concurrent_chunks: 5
|
|
|
|
max_concurrent_chunks: 25
|
|
|
|
|
|
|
|
|
|
|
|
- platform: moonshot
|
|
|
|
- platform: moonshot
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -710,10 +721,12 @@
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 30
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 30
|
|
|
|
|
|
|
|
|
|
|
|
- platform: deepinfra
|
|
|
|
- platform: deepinfra
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -760,42 +773,52 @@
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: BAAI/bge-base-en-v1.5
|
|
|
|
- name: BAAI/bge-base-en-v1.5
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: BAAI/bge-m3
|
|
|
|
- name: BAAI/bge-m3
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 8192
|
|
|
|
max_input_tokens: 8192
|
|
|
|
default_chunk_size: 2000
|
|
|
|
default_chunk_size: 2000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: intfloat/e5-base-v2
|
|
|
|
- name: intfloat/e5-base-v2
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: intfloat/e5-large-v2
|
|
|
|
- name: intfloat/e5-large-v2
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: intfloat/multilingual-e5-large
|
|
|
|
- name: intfloat/multilingual-e5-large
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: sentence-transformers/all-MiniLM-L6-v2
|
|
|
|
- name: sentence-transformers/all-MiniLM-L6-v2
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: sentence-transformers/paraphrase-MiniLM-L6-v2
|
|
|
|
- name: sentence-transformers/paraphrase-MiniLM-L6-v2
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: thenlper/gte-base
|
|
|
|
- name: thenlper/gte-base
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
|
|
|
|
|
|
|
|
- platform: fireworks
|
|
|
|
- platform: fireworks
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -853,18 +876,22 @@
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 8192
|
|
|
|
max_input_tokens: 8192
|
|
|
|
default_chunk_size: 1500
|
|
|
|
default_chunk_size: 1500
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: WhereIsAI/UAE-Large-V1
|
|
|
|
- name: WhereIsAI/UAE-Large-V1
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
- name: thenlper/gte-large
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: thenlper/gte-base
|
|
|
|
- name: thenlper/gte-base
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
|
|
|
|
|
|
|
|
- platform: openrouter
|
|
|
|
- platform: openrouter
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -1045,6 +1072,7 @@
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
|
|
|
|
|
|
|
|
- platform: together
|
|
|
|
- platform: together
|
|
|
|
# docs:
|
|
|
|
# docs:
|
|
|
@ -1080,27 +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
|
|
|
|
- name: togethercomputer/m2-bert-80M-2k-retrieval
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
mode: embedding
|
|
|
|
|
|
|
|
max_input_tokens: 2048
|
|
|
|
|
|
|
|
default_chunk_size: 1500
|
|
|
|
|
|
|
|
- name: togethercomputer/m2-bert-80M-8k-retrieval
|
|
|
|
|
|
|
|
mode: embedding
|
|
|
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
|
|
|
default_chunk_size: 1500
|
|
|
|
|
|
|
|
- name: togethercomputer/m2-bert-80M-32k-retrieval
|
|
|
|
|
|
|
|
mode: embedding
|
|
|
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
|
|
|
default_chunk_size: 1500
|
|
|
|
|
|
|
|
- name: WhereIsAI/UAE-Large-V1
|
|
|
|
- name: WhereIsAI/UAE-Large-V1
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: BAAI/bge-large-en-v1.5
|
|
|
|
- name: BAAI/bge-large-en-v1.5
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|
|
|
|
- name: BAAI/bge-base-en-v1.5
|
|
|
|
- name: BAAI/bge-base-en-v1.5
|
|
|
|
mode: embedding
|
|
|
|
mode: embedding
|
|
|
|
max_input_tokens: 512
|
|
|
|
max_input_tokens: 512
|
|
|
|
default_chunk_size: 1000
|
|
|
|
default_chunk_size: 1000
|
|
|
|
|
|
|
|
max_concurrent_chunks: 100
|