From 1a55e950aaaf9859ac7ff830e2932f5a248d1b37 Mon Sep 17 00:00:00 2001
From: Sergey Kozlov <skozlovf@gmail.com>
Date: Sat, 16 Mar 2024 07:33:51 +0600
Subject: [PATCH] community[patch]: support fastembed v1 and v2 (#19125)

**Description:**
#18040 forces `fastembed>2.0`, and this causes dependency conflicts with
the new `unstructured` package (different `onnxruntime`). There may be
other dependency conflicts.. The only way to use
`langchain-community>=0.0.28` is rollback to `unstructured 0.10.X`. But
new `unstructured` contains many fixes.

This PR allows to use both `fastembed` `v1` and `v2`.

How to reproduce:

`pyproject.toml`:
```toml
[tool.poetry]
name = "depstest"
version = "0.0.0"
description = "test"
authors = ["<dev@example.org>"]

[tool.poetry.dependencies]
python = ">=3.10,<3.12"
langchain-community = "^0.0.28"
fastembed = "^0.2.0"
unstructured = {extras = ["pdf"], version = "^0.12"}
```

```bash
$ poetry lock
```

Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>
---
 .../embeddings/fastembed.py                   | 29 ++++++++++++++-----
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/libs/community/langchain_community/embeddings/fastembed.py b/libs/community/langchain_community/embeddings/fastembed.py
index 65ed5b16c26..4f03ab70fe2 100644
--- a/libs/community/langchain_community/embeddings/fastembed.py
+++ b/libs/community/langchain_community/embeddings/fastembed.py
@@ -57,13 +57,15 @@ class FastEmbedEmbeddings(BaseModel, Embeddings):
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that FastEmbed has been installed."""
+        model_name = values.get("model_name")
+        max_length = values.get("max_length")
+        cache_dir = values.get("cache_dir")
+        threads = values.get("threads")
+
         try:
+            # >= v0.2.0
             from fastembed import TextEmbedding
 
-            model_name = values.get("model_name")
-            max_length = values.get("max_length")
-            cache_dir = values.get("cache_dir")
-            threads = values.get("threads")
             values["_model"] = TextEmbedding(
                 model_name=model_name,
                 max_length=max_length,
@@ -71,10 +73,21 @@ class FastEmbedEmbeddings(BaseModel, Embeddings):
                 threads=threads,
             )
         except ImportError as ie:
-            raise ImportError(
-                "'FastEmbedEmbeddings' requires 'fastembed==v0.2.0' or above. "
-                "Please install it with `pip install fastembed`."
-            ) from ie
+            try:
+                # < v0.2.0
+                from fastembed.embedding import FlagEmbedding
+
+                values["_model"] = FlagEmbedding(
+                    model_name=model_name,
+                    max_length=max_length,
+                    cache_dir=cache_dir,
+                    threads=threads,
+                )
+            except ImportError:
+                raise ImportError(
+                    "Could not import 'fastembed' Python package. "
+                    "Please install it with `pip install fastembed`."
+                ) from ie
         return values
 
     def embed_documents(self, texts: List[str]) -> List[List[float]]: