Skip to content

Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences

Merge branch 'v0.25-join' of https://github.com/ozanarmagan/typesense into v0.25-join

ozanarmagan222c50e2c171
diff --cc include/text_embedder.h
index f5419de9,e8f1de57..eeefea64
--- a/include/text_embedder.h
+++ b/include/text_embedder.h
@@@ -16,8 -16,8 +16,8 @@@ class TextEmbedder
// Constructor for remote models
TextEmbedder(const nlohmann::json& model_config);
~TextEmbedder();
- embedding_res_t Embed(const std::string& text);
- std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs, const size_t remote_embedding_batch_size = 0);
+ embedding_res_t Embed(const std::string& text, const size_t remote_embedder_timeout_ms = 30000, const size_t remote_embedding_num_try = 2);
- std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs);
++ std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs, const size_t remote_embedding_batch_size = 200);
const std::string& get_vocab_file_name() const;
bool is_remote() {
return remote_embedder_ != nullptr;
diff --cc include/text_embedder_remote.h
index d3a9bd3d,b72b26d5..4abaa9bd
--- a/include/text_embedder_remote.h
+++ b/include/text_embedder_remote.h
@@@ -28,8 -28,9 +28,9 @@@ class RemoteEmbedder
static long call_remote_api(const std::string& method, const std::string& url, const std::string& body, std::string& res_body, std::map<std::string, std::string>& headers, const std::unordered_map<std::string, std::string>& req_headers);
static inline ReplicationState* raft_server = nullptr;
public:
- virtual embedding_res_t Embed(const std::string& text) = 0;
+ virtual nlohmann::json get_error_json(const nlohmann::json& req_body, long res_code, const std::string& res_body) = 0;
+ virtual embedding_res_t Embed(const std::string& text, const size_t remote_embedder_timeout_ms = 30000, const size_t remote_embedding_num_try = 2) = 0;
- virtual std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs) = 0;
+ virtual std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs, const size_t remote_embedding_batch_size = 200) = 0;
static void init(ReplicationState* rs) {
raft_server = rs;
}
@@@ -47,8 -48,9 +48,9 @@@ class OpenAIEmbedder : public RemoteEmb
public:
OpenAIEmbedder(const std::string& openai_model_path, const std::string& api_key);
static Option<bool> is_model_valid(const nlohmann::json& model_config, unsigned int& num_dims);
- embedding_res_t Embed(const std::string& text) override;
+ embedding_res_t Embed(const std::string& text, const size_t remote_embedder_timeout_ms = 30000, const size_t remote_embedding_num_try = 2) override;
- std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs) override;
+ std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs, const size_t remote_embedding_batch_size = 200) override;
+ nlohmann::json get_error_json(const nlohmann::json& req_body, long res_code, const std::string& res_body) override;
};
@@@ -62,8 -65,9 +65,9 @@@ class GoogleEmbedder : public RemoteEmb
public:
GoogleEmbedder(const std::string& google_api_key);
static Option<bool> is_model_valid(const nlohmann::json& model_config, unsigned int& num_dims);
- embedding_res_t Embed(const std::string& text) override;
+ embedding_res_t Embed(const std::string& text, const size_t remote_embedder_timeout_ms = 30000, const size_t remote_embedding_num_try = 2) override;
- std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs) override;
+ std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs, const size_t remote_embedding_batch_size = 200) override;
+ nlohmann::json get_error_json(const nlohmann::json& req_body, long res_code, const std::string& res_body) override;
};
@@@ -88,8 -92,9 +92,9 @@@ class GCPEmbedder : public RemoteEmbedd
GCPEmbedder(const std::string& project_id, const std::string& model_name, const std::string& access_token,
const std::string& refresh_token, const std::string& client_id, const std::string& client_secret);
static Option<bool> is_model_valid(const nlohmann::json& model_config, unsigned int& num_dims);
- embedding_res_t Embed(const std::string& text) override;
+ embedding_res_t Embed(const std::string& text, const size_t remote_embedder_timeout_ms = 30000, const size_t remote_embedding_num_try = 2) override;
- std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs) override;
+ std::vector<embedding_res_t> batch_embed(const std::vector<std::string>& inputs, const size_t remote_embedding_batch_size = 200) override;
+ nlohmann::json get_error_json(const nlohmann::json& req_body, long res_code, const std::string& res_body) override;
};