summaryrefslogtreecommitdiffstats
path: root/src/client
AgeCommit message (Expand)AuthorLines
2024-07-26refactor: several optimizations (#749)sigoden-9/+0
2024-07-26feat: ollama support tools and new embeddings api (#748)sigoden-26/+80
2024-07-26feat: vertexai support mistral models (#746)sigoden-12/+42
2024-07-26feat: merge vertexai-cluade with vertexai (#745)sigoden-102/+59
2024-07-24fix: invalid tool_calls of qianwen client (#740)sigoden-33/+39
2024-07-22refactor: invalid model error message (#735)sigoden-1/+1
2024-07-17refactor: config creation prompt aware of env var (#722)sigoden-6/+14
2024-07-11refactor: improve estimate_token_length (#703)sigoden-15/+17
2024-07-11refactor: update models.yaml and abandon anyscale (#701)sigoden-7/+2
2024-06-28fix: gemini with functions that have empty parameters (#666)sigoden-1/+12
2024-06-27feat: implement native rag url loader (#660)sigoden-26/+4
2024-06-26refactor: improve azure-openai (#652)sigoden-3/+9
2024-06-25refactor: rename model type `rerank` to `reranker` (#646)sigoden-6/+6
2024-06-25feat: support rag-dedicated clients (jina and voyageai) (#645)sigoden-46/+186
2024-06-23refactor: embedding model add price and dimension (#636)sigoden-29/+51
2024-06-23refactor: remove reka client (#635)sigoden-125/+0
2024-06-23refactor: improve system message handling (#634)sigoden-6/+41
2024-06-22refactor: improve clients (#632)sigoden-42/+42
2024-06-22feat: ernie support function calling (#631)sigoden-8/+62
2024-06-22feat: ernie support embeddings and rereank (#630)sigoden-5/+101
2024-06-22refactor: some error messages (#627)sigoden-4/+4
2024-06-21refactor: rename model.max_concurrent_chunks to model.max_batch_size (#626)sigoden-7/+7
2024-06-21refactor: rename model.mode to model.type (#625)sigoden-8/+8
2024-06-21feat: serve embeddings api (#624)sigoden-2/+2
2024-06-21feat: cloudflare support embeddings (#623)sigoden-3/+50
2024-06-21feat: support rerank (#620)sigoden-28/+189
2024-06-19refactor: rag add rag_minimum_score config (#617)sigoden-2/+1
2024-06-19feat: qianwen support function calling (#616)sigoden-15/+110
2024-06-18feat: support reka client (#614)sigoden-0/+127
2024-06-18feat: support lingyiwanwu client (#613)sigoden-1/+2
2024-06-17fix: cohere tool use (#605)sigoden-19/+23
2024-06-17refactor: improve code quatity (#604)sigoden-3/+3
2024-06-15refactor: update models.yaml (#602)sigoden-2/+1
2024-06-14refactor: add/modify rag-related config (#599)sigoden-2/+9
2024-06-14chore: clippy and format (#600)sigoden-12/+0
2024-06-11refactor: improve openai client (#586)sigoden-1/+0
2024-06-11feat: support bot (#579)sigoden-5/+18
2024-06-05revert: feat: use systemInstruction for gemini-1.5-* models (#564) (#567)sigoden-10/+1
2024-06-05feat: use systemInstruction for gemini-1.5-* models (#564)sigoden-1/+10
2024-06-05chore: formatsigoden-29/+37
2024-06-05refactor: rename `pass_max_tokens` to `require_max_tokens` (#562)sigoden-4/+4
2024-06-05feat: support RAG (#560)sigoden-180/+604
2024-06-01refactor: rename some client structs and methods (#555)sigoden-248/+279
2024-05-30refactor: rename `SendData` to `CompletionData` (#553)sigoden-90/+141
2024-05-30chore: fix typossigoden-2/+2
2024-05-29refactor: use `json_stream` for ollama to improve reliability (#549)ProjectMoon-11/+11
2024-05-26fix: bedrock issues (#544)rolfwilms-0/+1
2024-05-23fix: json stream parser and refine client modules (#538)sigoden-227/+313
2024-05-23refactor: qiawen client add qwen-long (#537)sigoden-18/+26
2024-05-22feat: allow patching req body with client config (#534)sigoden-95/+133