fix: adjust max token size for openai ADA-v2 embeddings (#3793)

* Adjust max token size for openai ADA-v2 embeddings

* Added requested changes and corrected old seq len

Apparently the limit for the older models is 2046 and not 2048, I included this change directly. 
See (https://beta.openai.com/docs/guides/embeddings/what-are-embeddings) to check.

Author: LeoGitGuy

haystack/nodes/retriever/_embedding_encoder.py

@@ -391,30 +391,30 @@ def save(self, save_dir: Union[Path, str]):
 class _OpenAIEmbeddingEncoder(_BaseEmbeddingEncoder):
     def __init__(self, retriever: "EmbeddingRetriever"):
         # See https://beta.openai.com/docs/guides/embeddings for more details
-        # OpenAI has a max seq length of 2048 tokens and unknown max batch size
-        self.max_seq_len = min(2048, retriever.max_seq_len)
         self.url = "https://api.openai.com/v1/embeddings"
         self.api_key = retriever.api_key
         self.batch_size = min(64, retriever.batch_size)
         self.progress_bar = retriever.progress_bar
         model_class: str = next(
             (m for m in ["ada", "babbage", "davinci", "curie"] if m in retriever.embedding_model), "babbage"
         )
-        self._setup_encoding_models(model_class, retriever.embedding_model)
+        self._setup_encoding_models(model_class, retriever.embedding_model, retriever.max_seq_len)
 
         self.tokenizer = AutoTokenizer.from_pretrained("gpt2")
 
-    def _setup_encoding_models(self, model_class: str, model_name: str):
+    def _setup_encoding_models(self, model_class: str, model_name: str, max_seq_len: int):
         """
         Setup the encoding models for the retriever.
         """
         # new generation of embedding models (December 2022), we need to specify the full name
         if "text-embedding" in model_name:
             self.query_encoder_model = model_name
             self.doc_encoder_model = model_name
+            self.max_seq_len = min(8191, max_seq_len)
         else:
             self.query_encoder_model = f"text-search-{model_class}-query-001"
             self.doc_encoder_model = f"text-search-{model_class}-doc-001"
+            self.max_seq_len = min(2046, max_seq_len)
 
     def _ensure_text_limit(self, text: str) -> str:
         """